{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995213020584012,
  "eval_steps": 500,
  "global_step": 1044,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004786979415988511,
      "grad_norm": 0.24613235890865326,
      "learning_rate": 0.0002,
      "loss": 1.2771,
      "step": 5
    },
    {
      "epoch": 0.009573958831977022,
      "grad_norm": 0.16961899399757385,
      "learning_rate": 0.0002,
      "loss": 1.0713,
      "step": 10
    },
    {
      "epoch": 0.014360938247965534,
      "grad_norm": 0.15322890877723694,
      "learning_rate": 0.0002,
      "loss": 0.9605,
      "step": 15
    },
    {
      "epoch": 0.019147917663954045,
      "grad_norm": 0.1613943725824356,
      "learning_rate": 0.0002,
      "loss": 0.7417,
      "step": 20
    },
    {
      "epoch": 0.023934897079942556,
      "grad_norm": 0.15506355464458466,
      "learning_rate": 0.0002,
      "loss": 0.6595,
      "step": 25
    },
    {
      "epoch": 0.028721876495931067,
      "grad_norm": 0.1182127594947815,
      "learning_rate": 0.0002,
      "loss": 0.6764,
      "step": 30
    },
    {
      "epoch": 0.03350885591191958,
      "grad_norm": 0.10777570307254791,
      "learning_rate": 0.0002,
      "loss": 0.6284,
      "step": 35
    },
    {
      "epoch": 0.03829583532790809,
      "grad_norm": 0.08354483544826508,
      "learning_rate": 0.0002,
      "loss": 0.6242,
      "step": 40
    },
    {
      "epoch": 0.0430828147438966,
      "grad_norm": 0.09534800797700882,
      "learning_rate": 0.0002,
      "loss": 0.6214,
      "step": 45
    },
    {
      "epoch": 0.04786979415988511,
      "grad_norm": 0.10349296033382416,
      "learning_rate": 0.0002,
      "loss": 0.6159,
      "step": 50
    },
    {
      "epoch": 0.052656773575873624,
      "grad_norm": 0.08007140457630157,
      "learning_rate": 0.0002,
      "loss": 0.5848,
      "step": 55
    },
    {
      "epoch": 0.057443752991862135,
      "grad_norm": 0.07333367317914963,
      "learning_rate": 0.0002,
      "loss": 0.6728,
      "step": 60
    },
    {
      "epoch": 0.062230732407850646,
      "grad_norm": 0.07483084499835968,
      "learning_rate": 0.0002,
      "loss": 0.5873,
      "step": 65
    },
    {
      "epoch": 0.06701771182383916,
      "grad_norm": 0.07768324017524719,
      "learning_rate": 0.0002,
      "loss": 0.6175,
      "step": 70
    },
    {
      "epoch": 0.07180469123982768,
      "grad_norm": 0.07919920980930328,
      "learning_rate": 0.0002,
      "loss": 0.5256,
      "step": 75
    },
    {
      "epoch": 0.07659167065581618,
      "grad_norm": 0.09047867357730865,
      "learning_rate": 0.0002,
      "loss": 0.5968,
      "step": 80
    },
    {
      "epoch": 0.0813786500718047,
      "grad_norm": 0.08032748848199844,
      "learning_rate": 0.0002,
      "loss": 0.6136,
      "step": 85
    },
    {
      "epoch": 0.0861656294877932,
      "grad_norm": 0.0846623107790947,
      "learning_rate": 0.0002,
      "loss": 0.5491,
      "step": 90
    },
    {
      "epoch": 0.09095260890378172,
      "grad_norm": 0.0998520776629448,
      "learning_rate": 0.0002,
      "loss": 0.5526,
      "step": 95
    },
    {
      "epoch": 0.09573958831977022,
      "grad_norm": 0.08374989777803421,
      "learning_rate": 0.0002,
      "loss": 0.5713,
      "step": 100
    },
    {
      "epoch": 0.10052656773575874,
      "grad_norm": 0.07846508920192719,
      "learning_rate": 0.0002,
      "loss": 0.5801,
      "step": 105
    },
    {
      "epoch": 0.10531354715174725,
      "grad_norm": 0.08031659573316574,
      "learning_rate": 0.0002,
      "loss": 0.6147,
      "step": 110
    },
    {
      "epoch": 0.11010052656773577,
      "grad_norm": 0.08738347887992859,
      "learning_rate": 0.0002,
      "loss": 0.5208,
      "step": 115
    },
    {
      "epoch": 0.11488750598372427,
      "grad_norm": 0.0916195958852768,
      "learning_rate": 0.0002,
      "loss": 0.5689,
      "step": 120
    },
    {
      "epoch": 0.11967448539971279,
      "grad_norm": 0.08580000698566437,
      "learning_rate": 0.0002,
      "loss": 0.6158,
      "step": 125
    },
    {
      "epoch": 0.12446146481570129,
      "grad_norm": 0.08231440931558609,
      "learning_rate": 0.0002,
      "loss": 0.5989,
      "step": 130
    },
    {
      "epoch": 0.1292484442316898,
      "grad_norm": 0.09185798466205597,
      "learning_rate": 0.0002,
      "loss": 0.5117,
      "step": 135
    },
    {
      "epoch": 0.13403542364767831,
      "grad_norm": 0.0896279439330101,
      "learning_rate": 0.0002,
      "loss": 0.4921,
      "step": 140
    },
    {
      "epoch": 0.13882240306366683,
      "grad_norm": 0.08800848573446274,
      "learning_rate": 0.0002,
      "loss": 0.5737,
      "step": 145
    },
    {
      "epoch": 0.14360938247965535,
      "grad_norm": 0.08985792100429535,
      "learning_rate": 0.0002,
      "loss": 0.5814,
      "step": 150
    },
    {
      "epoch": 0.14839636189564384,
      "grad_norm": 0.096456378698349,
      "learning_rate": 0.0002,
      "loss": 0.5483,
      "step": 155
    },
    {
      "epoch": 0.15318334131163236,
      "grad_norm": 0.08564233034849167,
      "learning_rate": 0.0002,
      "loss": 0.5258,
      "step": 160
    },
    {
      "epoch": 0.15797032072762088,
      "grad_norm": 0.08352309465408325,
      "learning_rate": 0.0002,
      "loss": 0.516,
      "step": 165
    },
    {
      "epoch": 0.1627573001436094,
      "grad_norm": 0.08917209506034851,
      "learning_rate": 0.0002,
      "loss": 0.5133,
      "step": 170
    },
    {
      "epoch": 0.1675442795595979,
      "grad_norm": 0.08113600313663483,
      "learning_rate": 0.0002,
      "loss": 0.556,
      "step": 175
    },
    {
      "epoch": 0.1723312589755864,
      "grad_norm": 0.09329506009817123,
      "learning_rate": 0.0002,
      "loss": 0.5211,
      "step": 180
    },
    {
      "epoch": 0.17711823839157492,
      "grad_norm": 0.08815263211727142,
      "learning_rate": 0.0002,
      "loss": 0.5338,
      "step": 185
    },
    {
      "epoch": 0.18190521780756344,
      "grad_norm": 0.08324268460273743,
      "learning_rate": 0.0002,
      "loss": 0.5066,
      "step": 190
    },
    {
      "epoch": 0.18669219722355193,
      "grad_norm": 0.0860678032040596,
      "learning_rate": 0.0002,
      "loss": 0.5745,
      "step": 195
    },
    {
      "epoch": 0.19147917663954045,
      "grad_norm": 0.07750646024942398,
      "learning_rate": 0.0002,
      "loss": 0.4632,
      "step": 200
    },
    {
      "epoch": 0.19626615605552897,
      "grad_norm": 0.09053143113851547,
      "learning_rate": 0.0002,
      "loss": 0.5797,
      "step": 205
    },
    {
      "epoch": 0.20105313547151749,
      "grad_norm": 0.07899998128414154,
      "learning_rate": 0.0002,
      "loss": 0.6043,
      "step": 210
    },
    {
      "epoch": 0.20584011488750598,
      "grad_norm": 0.09660762548446655,
      "learning_rate": 0.0002,
      "loss": 0.5559,
      "step": 215
    },
    {
      "epoch": 0.2106270943034945,
      "grad_norm": 0.0966796949505806,
      "learning_rate": 0.0002,
      "loss": 0.5965,
      "step": 220
    },
    {
      "epoch": 0.215414073719483,
      "grad_norm": 0.10608462989330292,
      "learning_rate": 0.0002,
      "loss": 0.4921,
      "step": 225
    },
    {
      "epoch": 0.22020105313547153,
      "grad_norm": 0.07869511842727661,
      "learning_rate": 0.0002,
      "loss": 0.5416,
      "step": 230
    },
    {
      "epoch": 0.22498803255146002,
      "grad_norm": 0.10257625579833984,
      "learning_rate": 0.0002,
      "loss": 0.5703,
      "step": 235
    },
    {
      "epoch": 0.22977501196744854,
      "grad_norm": 0.09301017224788666,
      "learning_rate": 0.0002,
      "loss": 0.5955,
      "step": 240
    },
    {
      "epoch": 0.23456199138343706,
      "grad_norm": 0.08770053088665009,
      "learning_rate": 0.0002,
      "loss": 0.4946,
      "step": 245
    },
    {
      "epoch": 0.23934897079942558,
      "grad_norm": 0.09587664902210236,
      "learning_rate": 0.0002,
      "loss": 0.5322,
      "step": 250
    },
    {
      "epoch": 0.24413595021541407,
      "grad_norm": 0.082343190908432,
      "learning_rate": 0.0002,
      "loss": 0.6184,
      "step": 255
    },
    {
      "epoch": 0.24892292963140258,
      "grad_norm": 0.09046710282564163,
      "learning_rate": 0.0002,
      "loss": 0.5508,
      "step": 260
    },
    {
      "epoch": 0.2537099090473911,
      "grad_norm": 0.09608398377895355,
      "learning_rate": 0.0002,
      "loss": 0.5634,
      "step": 265
    },
    {
      "epoch": 0.2584968884633796,
      "grad_norm": 0.08927994221448898,
      "learning_rate": 0.0002,
      "loss": 0.5631,
      "step": 270
    },
    {
      "epoch": 0.26328386787936814,
      "grad_norm": 0.115423783659935,
      "learning_rate": 0.0002,
      "loss": 0.5898,
      "step": 275
    },
    {
      "epoch": 0.26807084729535663,
      "grad_norm": 0.0849870815873146,
      "learning_rate": 0.0002,
      "loss": 0.5095,
      "step": 280
    },
    {
      "epoch": 0.2728578267113451,
      "grad_norm": 0.09704048186540604,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 285
    },
    {
      "epoch": 0.27764480612733367,
      "grad_norm": 0.0753026083111763,
      "learning_rate": 0.0002,
      "loss": 0.496,
      "step": 290
    },
    {
      "epoch": 0.28243178554332216,
      "grad_norm": 0.09067820757627487,
      "learning_rate": 0.0002,
      "loss": 0.5093,
      "step": 295
    },
    {
      "epoch": 0.2872187649593107,
      "grad_norm": 0.09334460645914078,
      "learning_rate": 0.0002,
      "loss": 0.5467,
      "step": 300
    },
    {
      "epoch": 0.2920057443752992,
      "grad_norm": 0.09724689275026321,
      "learning_rate": 0.0002,
      "loss": 0.5533,
      "step": 305
    },
    {
      "epoch": 0.2967927237912877,
      "grad_norm": 0.09164885431528091,
      "learning_rate": 0.0002,
      "loss": 0.5436,
      "step": 310
    },
    {
      "epoch": 0.30157970320727623,
      "grad_norm": 0.09583573043346405,
      "learning_rate": 0.0002,
      "loss": 0.5408,
      "step": 315
    },
    {
      "epoch": 0.3063666826232647,
      "grad_norm": 0.0860954225063324,
      "learning_rate": 0.0002,
      "loss": 0.4828,
      "step": 320
    },
    {
      "epoch": 0.3111536620392532,
      "grad_norm": 0.08259189128875732,
      "learning_rate": 0.0002,
      "loss": 0.582,
      "step": 325
    },
    {
      "epoch": 0.31594064145524176,
      "grad_norm": 0.10501275211572647,
      "learning_rate": 0.0002,
      "loss": 0.5176,
      "step": 330
    },
    {
      "epoch": 0.32072762087123025,
      "grad_norm": 0.09174875169992447,
      "learning_rate": 0.0002,
      "loss": 0.5393,
      "step": 335
    },
    {
      "epoch": 0.3255146002872188,
      "grad_norm": 0.09675736725330353,
      "learning_rate": 0.0002,
      "loss": 0.5495,
      "step": 340
    },
    {
      "epoch": 0.3303015797032073,
      "grad_norm": 0.08207903057336807,
      "learning_rate": 0.0002,
      "loss": 0.5252,
      "step": 345
    },
    {
      "epoch": 0.3350885591191958,
      "grad_norm": 0.08642390370368958,
      "learning_rate": 0.0002,
      "loss": 0.5688,
      "step": 350
    },
    {
      "epoch": 0.3398755385351843,
      "grad_norm": 0.0861140564084053,
      "learning_rate": 0.0002,
      "loss": 0.4866,
      "step": 355
    },
    {
      "epoch": 0.3446625179511728,
      "grad_norm": 0.08826491981744766,
      "learning_rate": 0.0002,
      "loss": 0.5392,
      "step": 360
    },
    {
      "epoch": 0.3494494973671613,
      "grad_norm": 0.09024737030267715,
      "learning_rate": 0.0002,
      "loss": 0.5554,
      "step": 365
    },
    {
      "epoch": 0.35423647678314985,
      "grad_norm": 0.09096304327249527,
      "learning_rate": 0.0002,
      "loss": 0.516,
      "step": 370
    },
    {
      "epoch": 0.35902345619913834,
      "grad_norm": 0.0845038965344429,
      "learning_rate": 0.0002,
      "loss": 0.5301,
      "step": 375
    },
    {
      "epoch": 0.3638104356151269,
      "grad_norm": 0.08174905180931091,
      "learning_rate": 0.0002,
      "loss": 0.5472,
      "step": 380
    },
    {
      "epoch": 0.36859741503111537,
      "grad_norm": 0.08673607558012009,
      "learning_rate": 0.0002,
      "loss": 0.5648,
      "step": 385
    },
    {
      "epoch": 0.37338439444710386,
      "grad_norm": 0.08147840946912766,
      "learning_rate": 0.0002,
      "loss": 0.5317,
      "step": 390
    },
    {
      "epoch": 0.3781713738630924,
      "grad_norm": 0.08197998255491257,
      "learning_rate": 0.0002,
      "loss": 0.5085,
      "step": 395
    },
    {
      "epoch": 0.3829583532790809,
      "grad_norm": 0.09027797728776932,
      "learning_rate": 0.0002,
      "loss": 0.5488,
      "step": 400
    },
    {
      "epoch": 0.3877453326950694,
      "grad_norm": 0.08635086566209793,
      "learning_rate": 0.0002,
      "loss": 0.5182,
      "step": 405
    },
    {
      "epoch": 0.39253231211105793,
      "grad_norm": 0.09970038384199142,
      "learning_rate": 0.0002,
      "loss": 0.5852,
      "step": 410
    },
    {
      "epoch": 0.3973192915270464,
      "grad_norm": 0.08561892062425613,
      "learning_rate": 0.0002,
      "loss": 0.5144,
      "step": 415
    },
    {
      "epoch": 0.40210627094303497,
      "grad_norm": 0.08953725546598434,
      "learning_rate": 0.0002,
      "loss": 0.5064,
      "step": 420
    },
    {
      "epoch": 0.40689325035902346,
      "grad_norm": 0.09641014784574509,
      "learning_rate": 0.0002,
      "loss": 0.4849,
      "step": 425
    },
    {
      "epoch": 0.41168022977501195,
      "grad_norm": 0.09051619470119476,
      "learning_rate": 0.0002,
      "loss": 0.5777,
      "step": 430
    },
    {
      "epoch": 0.4164672091910005,
      "grad_norm": 0.08543870598077774,
      "learning_rate": 0.0002,
      "loss": 0.5299,
      "step": 435
    },
    {
      "epoch": 0.421254188606989,
      "grad_norm": 0.08574735373258591,
      "learning_rate": 0.0002,
      "loss": 0.5573,
      "step": 440
    },
    {
      "epoch": 0.4260411680229775,
      "grad_norm": 0.09401609748601913,
      "learning_rate": 0.0002,
      "loss": 0.5643,
      "step": 445
    },
    {
      "epoch": 0.430828147438966,
      "grad_norm": 0.10760053247213364,
      "learning_rate": 0.0002,
      "loss": 0.516,
      "step": 450
    },
    {
      "epoch": 0.4356151268549545,
      "grad_norm": 0.09510120749473572,
      "learning_rate": 0.0002,
      "loss": 0.505,
      "step": 455
    },
    {
      "epoch": 0.44040210627094306,
      "grad_norm": 0.09105115383863449,
      "learning_rate": 0.0002,
      "loss": 0.5717,
      "step": 460
    },
    {
      "epoch": 0.44518908568693155,
      "grad_norm": 0.0891876295208931,
      "learning_rate": 0.0002,
      "loss": 0.5258,
      "step": 465
    },
    {
      "epoch": 0.44997606510292004,
      "grad_norm": 0.08933177590370178,
      "learning_rate": 0.0002,
      "loss": 0.4951,
      "step": 470
    },
    {
      "epoch": 0.4547630445189086,
      "grad_norm": 0.09821013361215591,
      "learning_rate": 0.0002,
      "loss": 0.5422,
      "step": 475
    },
    {
      "epoch": 0.4595500239348971,
      "grad_norm": 0.090922050178051,
      "learning_rate": 0.0002,
      "loss": 0.5286,
      "step": 480
    },
    {
      "epoch": 0.46433700335088557,
      "grad_norm": 0.09325899183750153,
      "learning_rate": 0.0002,
      "loss": 0.596,
      "step": 485
    },
    {
      "epoch": 0.4691239827668741,
      "grad_norm": 0.09565772861242294,
      "learning_rate": 0.0002,
      "loss": 0.4855,
      "step": 490
    },
    {
      "epoch": 0.4739109621828626,
      "grad_norm": 0.08238258212804794,
      "learning_rate": 0.0002,
      "loss": 0.534,
      "step": 495
    },
    {
      "epoch": 0.47869794159885115,
      "grad_norm": 0.10455012321472168,
      "learning_rate": 0.0002,
      "loss": 0.5615,
      "step": 500
    },
    {
      "epoch": 0.48348492101483964,
      "grad_norm": 0.07809582352638245,
      "learning_rate": 0.0002,
      "loss": 0.5319,
      "step": 505
    },
    {
      "epoch": 0.48827190043082813,
      "grad_norm": 0.09158290922641754,
      "learning_rate": 0.0002,
      "loss": 0.5149,
      "step": 510
    },
    {
      "epoch": 0.4930588798468167,
      "grad_norm": 0.09475893527269363,
      "learning_rate": 0.0002,
      "loss": 0.5548,
      "step": 515
    },
    {
      "epoch": 0.49784585926280517,
      "grad_norm": 0.08862445503473282,
      "learning_rate": 0.0002,
      "loss": 0.551,
      "step": 520
    },
    {
      "epoch": 0.5026328386787937,
      "grad_norm": 0.08608075976371765,
      "learning_rate": 0.0002,
      "loss": 0.5032,
      "step": 525
    },
    {
      "epoch": 0.5074198180947822,
      "grad_norm": 0.09171325713396072,
      "learning_rate": 0.0002,
      "loss": 0.4872,
      "step": 530
    },
    {
      "epoch": 0.5122067975107707,
      "grad_norm": 0.08891316503286362,
      "learning_rate": 0.0002,
      "loss": 0.5381,
      "step": 535
    },
    {
      "epoch": 0.5169937769267592,
      "grad_norm": 0.09202417731285095,
      "learning_rate": 0.0002,
      "loss": 0.5642,
      "step": 540
    },
    {
      "epoch": 0.5217807563427477,
      "grad_norm": 0.09024330973625183,
      "learning_rate": 0.0002,
      "loss": 0.4638,
      "step": 545
    },
    {
      "epoch": 0.5265677357587363,
      "grad_norm": 0.08484344184398651,
      "learning_rate": 0.0002,
      "loss": 0.5171,
      "step": 550
    },
    {
      "epoch": 0.5313547151747248,
      "grad_norm": 0.09126883000135422,
      "learning_rate": 0.0002,
      "loss": 0.4778,
      "step": 555
    },
    {
      "epoch": 0.5361416945907133,
      "grad_norm": 0.08565142005681992,
      "learning_rate": 0.0002,
      "loss": 0.5264,
      "step": 560
    },
    {
      "epoch": 0.5409286740067017,
      "grad_norm": 0.09363921731710434,
      "learning_rate": 0.0002,
      "loss": 0.5261,
      "step": 565
    },
    {
      "epoch": 0.5457156534226902,
      "grad_norm": 0.08321545273065567,
      "learning_rate": 0.0002,
      "loss": 0.4724,
      "step": 570
    },
    {
      "epoch": 0.5505026328386788,
      "grad_norm": 0.08636103570461273,
      "learning_rate": 0.0002,
      "loss": 0.5383,
      "step": 575
    },
    {
      "epoch": 0.5552896122546673,
      "grad_norm": 0.0867634192109108,
      "learning_rate": 0.0002,
      "loss": 0.571,
      "step": 580
    },
    {
      "epoch": 0.5600765916706558,
      "grad_norm": 0.09202156215906143,
      "learning_rate": 0.0002,
      "loss": 0.4925,
      "step": 585
    },
    {
      "epoch": 0.5648635710866443,
      "grad_norm": 0.08338255435228348,
      "learning_rate": 0.0002,
      "loss": 0.4724,
      "step": 590
    },
    {
      "epoch": 0.5696505505026328,
      "grad_norm": 0.09248416125774384,
      "learning_rate": 0.0002,
      "loss": 0.5339,
      "step": 595
    },
    {
      "epoch": 0.5744375299186214,
      "grad_norm": 0.08971364796161652,
      "learning_rate": 0.0002,
      "loss": 0.5467,
      "step": 600
    },
    {
      "epoch": 0.5792245093346099,
      "grad_norm": 0.10297700017690659,
      "learning_rate": 0.0002,
      "loss": 0.5269,
      "step": 605
    },
    {
      "epoch": 0.5840114887505984,
      "grad_norm": 0.09885570406913757,
      "learning_rate": 0.0002,
      "loss": 0.5741,
      "step": 610
    },
    {
      "epoch": 0.5887984681665869,
      "grad_norm": 0.0943949893116951,
      "learning_rate": 0.0002,
      "loss": 0.5107,
      "step": 615
    },
    {
      "epoch": 0.5935854475825754,
      "grad_norm": 0.09385235607624054,
      "learning_rate": 0.0002,
      "loss": 0.5522,
      "step": 620
    },
    {
      "epoch": 0.5983724269985639,
      "grad_norm": 0.0906907171010971,
      "learning_rate": 0.0002,
      "loss": 0.4684,
      "step": 625
    },
    {
      "epoch": 0.6031594064145525,
      "grad_norm": 0.08867505192756653,
      "learning_rate": 0.0002,
      "loss": 0.4637,
      "step": 630
    },
    {
      "epoch": 0.607946385830541,
      "grad_norm": 0.0929451733827591,
      "learning_rate": 0.0002,
      "loss": 0.5462,
      "step": 635
    },
    {
      "epoch": 0.6127333652465294,
      "grad_norm": 0.08720085769891739,
      "learning_rate": 0.0002,
      "loss": 0.497,
      "step": 640
    },
    {
      "epoch": 0.6175203446625179,
      "grad_norm": 0.10713039338588715,
      "learning_rate": 0.0002,
      "loss": 0.5448,
      "step": 645
    },
    {
      "epoch": 0.6223073240785064,
      "grad_norm": 0.08213481307029724,
      "learning_rate": 0.0002,
      "loss": 0.4816,
      "step": 650
    },
    {
      "epoch": 0.627094303494495,
      "grad_norm": 0.08939921110868454,
      "learning_rate": 0.0002,
      "loss": 0.4883,
      "step": 655
    },
    {
      "epoch": 0.6318812829104835,
      "grad_norm": 0.09071970731019974,
      "learning_rate": 0.0002,
      "loss": 0.5411,
      "step": 660
    },
    {
      "epoch": 0.636668262326472,
      "grad_norm": 0.09525053203105927,
      "learning_rate": 0.0002,
      "loss": 0.4966,
      "step": 665
    },
    {
      "epoch": 0.6414552417424605,
      "grad_norm": 0.08770790696144104,
      "learning_rate": 0.0002,
      "loss": 0.4786,
      "step": 670
    },
    {
      "epoch": 0.646242221158449,
      "grad_norm": 0.08054076880216599,
      "learning_rate": 0.0002,
      "loss": 0.5051,
      "step": 675
    },
    {
      "epoch": 0.6510292005744376,
      "grad_norm": 0.08313776552677155,
      "learning_rate": 0.0002,
      "loss": 0.5547,
      "step": 680
    },
    {
      "epoch": 0.6558161799904261,
      "grad_norm": 0.0805881917476654,
      "learning_rate": 0.0002,
      "loss": 0.495,
      "step": 685
    },
    {
      "epoch": 0.6606031594064146,
      "grad_norm": 0.10019008070230484,
      "learning_rate": 0.0002,
      "loss": 0.4683,
      "step": 690
    },
    {
      "epoch": 0.665390138822403,
      "grad_norm": 0.08097992837429047,
      "learning_rate": 0.0002,
      "loss": 0.5511,
      "step": 695
    },
    {
      "epoch": 0.6701771182383915,
      "grad_norm": 0.08138570934534073,
      "learning_rate": 0.0002,
      "loss": 0.5638,
      "step": 700
    },
    {
      "epoch": 0.67496409765438,
      "grad_norm": 0.09005066752433777,
      "learning_rate": 0.0002,
      "loss": 0.4591,
      "step": 705
    },
    {
      "epoch": 0.6797510770703686,
      "grad_norm": 0.09737958759069443,
      "learning_rate": 0.0002,
      "loss": 0.5003,
      "step": 710
    },
    {
      "epoch": 0.6845380564863571,
      "grad_norm": 0.0959305465221405,
      "learning_rate": 0.0002,
      "loss": 0.5645,
      "step": 715
    },
    {
      "epoch": 0.6893250359023456,
      "grad_norm": 0.0876409187912941,
      "learning_rate": 0.0002,
      "loss": 0.531,
      "step": 720
    },
    {
      "epoch": 0.6941120153183341,
      "grad_norm": 0.09579559415578842,
      "learning_rate": 0.0002,
      "loss": 0.5717,
      "step": 725
    },
    {
      "epoch": 0.6988989947343226,
      "grad_norm": 0.08657323569059372,
      "learning_rate": 0.0002,
      "loss": 0.4846,
      "step": 730
    },
    {
      "epoch": 0.7036859741503112,
      "grad_norm": 0.08424372225999832,
      "learning_rate": 0.0002,
      "loss": 0.5175,
      "step": 735
    },
    {
      "epoch": 0.7084729535662997,
      "grad_norm": 0.0895078107714653,
      "learning_rate": 0.0002,
      "loss": 0.518,
      "step": 740
    },
    {
      "epoch": 0.7132599329822882,
      "grad_norm": 0.08580939471721649,
      "learning_rate": 0.0002,
      "loss": 0.5601,
      "step": 745
    },
    {
      "epoch": 0.7180469123982767,
      "grad_norm": 0.0797315239906311,
      "learning_rate": 0.0002,
      "loss": 0.5354,
      "step": 750
    },
    {
      "epoch": 0.7228338918142652,
      "grad_norm": 0.08981385827064514,
      "learning_rate": 0.0002,
      "loss": 0.5638,
      "step": 755
    },
    {
      "epoch": 0.7276208712302538,
      "grad_norm": 0.09025374054908752,
      "learning_rate": 0.0002,
      "loss": 0.5028,
      "step": 760
    },
    {
      "epoch": 0.7324078506462423,
      "grad_norm": 0.09753820300102234,
      "learning_rate": 0.0002,
      "loss": 0.5237,
      "step": 765
    },
    {
      "epoch": 0.7371948300622307,
      "grad_norm": 0.08967633545398712,
      "learning_rate": 0.0002,
      "loss": 0.4636,
      "step": 770
    },
    {
      "epoch": 0.7419818094782192,
      "grad_norm": 0.10074934363365173,
      "learning_rate": 0.0002,
      "loss": 0.5276,
      "step": 775
    },
    {
      "epoch": 0.7467687888942077,
      "grad_norm": 0.0874541625380516,
      "learning_rate": 0.0002,
      "loss": 0.5085,
      "step": 780
    },
    {
      "epoch": 0.7515557683101962,
      "grad_norm": 0.084027960896492,
      "learning_rate": 0.0002,
      "loss": 0.5062,
      "step": 785
    },
    {
      "epoch": 0.7563427477261848,
      "grad_norm": 0.08965150266885757,
      "learning_rate": 0.0002,
      "loss": 0.5214,
      "step": 790
    },
    {
      "epoch": 0.7611297271421733,
      "grad_norm": 0.08234406262636185,
      "learning_rate": 0.0002,
      "loss": 0.4863,
      "step": 795
    },
    {
      "epoch": 0.7659167065581618,
      "grad_norm": 0.08266417682170868,
      "learning_rate": 0.0002,
      "loss": 0.5149,
      "step": 800
    },
    {
      "epoch": 0.7707036859741503,
      "grad_norm": 0.08559945225715637,
      "learning_rate": 0.0002,
      "loss": 0.528,
      "step": 805
    },
    {
      "epoch": 0.7754906653901388,
      "grad_norm": 0.08358705043792725,
      "learning_rate": 0.0002,
      "loss": 0.5283,
      "step": 810
    },
    {
      "epoch": 0.7802776448061274,
      "grad_norm": 0.08530480414628983,
      "learning_rate": 0.0002,
      "loss": 0.4868,
      "step": 815
    },
    {
      "epoch": 0.7850646242221159,
      "grad_norm": 0.08576823025941849,
      "learning_rate": 0.0002,
      "loss": 0.5277,
      "step": 820
    },
    {
      "epoch": 0.7898516036381044,
      "grad_norm": 0.10152282565832138,
      "learning_rate": 0.0002,
      "loss": 0.4652,
      "step": 825
    },
    {
      "epoch": 0.7946385830540929,
      "grad_norm": 0.08843079209327698,
      "learning_rate": 0.0002,
      "loss": 0.5194,
      "step": 830
    },
    {
      "epoch": 0.7994255624700813,
      "grad_norm": 0.08835287392139435,
      "learning_rate": 0.0002,
      "loss": 0.5352,
      "step": 835
    },
    {
      "epoch": 0.8042125418860699,
      "grad_norm": 0.08630600571632385,
      "learning_rate": 0.0002,
      "loss": 0.4869,
      "step": 840
    },
    {
      "epoch": 0.8089995213020584,
      "grad_norm": 0.08701962232589722,
      "learning_rate": 0.0002,
      "loss": 0.5048,
      "step": 845
    },
    {
      "epoch": 0.8137865007180469,
      "grad_norm": 0.09896954894065857,
      "learning_rate": 0.0002,
      "loss": 0.5398,
      "step": 850
    },
    {
      "epoch": 0.8185734801340354,
      "grad_norm": 0.0876292958855629,
      "learning_rate": 0.0002,
      "loss": 0.5801,
      "step": 855
    },
    {
      "epoch": 0.8233604595500239,
      "grad_norm": 0.08727893233299255,
      "learning_rate": 0.0002,
      "loss": 0.5378,
      "step": 860
    },
    {
      "epoch": 0.8281474389660124,
      "grad_norm": 0.08662202209234238,
      "learning_rate": 0.0002,
      "loss": 0.5804,
      "step": 865
    },
    {
      "epoch": 0.832934418382001,
      "grad_norm": 0.08253654092550278,
      "learning_rate": 0.0002,
      "loss": 0.4701,
      "step": 870
    },
    {
      "epoch": 0.8377213977979895,
      "grad_norm": 0.08907407522201538,
      "learning_rate": 0.0002,
      "loss": 0.4918,
      "step": 875
    },
    {
      "epoch": 0.842508377213978,
      "grad_norm": 0.09331085532903671,
      "learning_rate": 0.0002,
      "loss": 0.5438,
      "step": 880
    },
    {
      "epoch": 0.8472953566299665,
      "grad_norm": 0.09129630029201508,
      "learning_rate": 0.0002,
      "loss": 0.5327,
      "step": 885
    },
    {
      "epoch": 0.852082336045955,
      "grad_norm": 0.09735500812530518,
      "learning_rate": 0.0002,
      "loss": 0.5281,
      "step": 890
    },
    {
      "epoch": 0.8568693154619436,
      "grad_norm": 0.0904528871178627,
      "learning_rate": 0.0002,
      "loss": 0.4964,
      "step": 895
    },
    {
      "epoch": 0.861656294877932,
      "grad_norm": 0.08291352540254593,
      "learning_rate": 0.0002,
      "loss": 0.5192,
      "step": 900
    },
    {
      "epoch": 0.8664432742939205,
      "grad_norm": 0.09108038246631622,
      "learning_rate": 0.0002,
      "loss": 0.501,
      "step": 905
    },
    {
      "epoch": 0.871230253709909,
      "grad_norm": 0.09137269854545593,
      "learning_rate": 0.0002,
      "loss": 0.5012,
      "step": 910
    },
    {
      "epoch": 0.8760172331258975,
      "grad_norm": 0.08169892430305481,
      "learning_rate": 0.0002,
      "loss": 0.4994,
      "step": 915
    },
    {
      "epoch": 0.8808042125418861,
      "grad_norm": 0.08467283844947815,
      "learning_rate": 0.0002,
      "loss": 0.4502,
      "step": 920
    },
    {
      "epoch": 0.8855911919578746,
      "grad_norm": 0.08680226653814316,
      "learning_rate": 0.0002,
      "loss": 0.5508,
      "step": 925
    },
    {
      "epoch": 0.8903781713738631,
      "grad_norm": 0.08897334337234497,
      "learning_rate": 0.0002,
      "loss": 0.5281,
      "step": 930
    },
    {
      "epoch": 0.8951651507898516,
      "grad_norm": 0.09124335646629333,
      "learning_rate": 0.0002,
      "loss": 0.5173,
      "step": 935
    },
    {
      "epoch": 0.8999521302058401,
      "grad_norm": 0.08976174145936966,
      "learning_rate": 0.0002,
      "loss": 0.5519,
      "step": 940
    },
    {
      "epoch": 0.9047391096218286,
      "grad_norm": 0.07799748331308365,
      "learning_rate": 0.0002,
      "loss": 0.5495,
      "step": 945
    },
    {
      "epoch": 0.9095260890378172,
      "grad_norm": 0.08304045349359512,
      "learning_rate": 0.0002,
      "loss": 0.5552,
      "step": 950
    },
    {
      "epoch": 0.9143130684538057,
      "grad_norm": 0.08134391158819199,
      "learning_rate": 0.0002,
      "loss": 0.4953,
      "step": 955
    },
    {
      "epoch": 0.9191000478697942,
      "grad_norm": 0.102556973695755,
      "learning_rate": 0.0002,
      "loss": 0.5841,
      "step": 960
    },
    {
      "epoch": 0.9238870272857826,
      "grad_norm": 0.09310037642717361,
      "learning_rate": 0.0002,
      "loss": 0.4977,
      "step": 965
    },
    {
      "epoch": 0.9286740067017711,
      "grad_norm": 0.08947998285293579,
      "learning_rate": 0.0002,
      "loss": 0.5147,
      "step": 970
    },
    {
      "epoch": 0.9334609861177597,
      "grad_norm": 0.0801323875784874,
      "learning_rate": 0.0002,
      "loss": 0.5379,
      "step": 975
    },
    {
      "epoch": 0.9382479655337482,
      "grad_norm": 0.09458567947149277,
      "learning_rate": 0.0002,
      "loss": 0.463,
      "step": 980
    },
    {
      "epoch": 0.9430349449497367,
      "grad_norm": 0.08248139917850494,
      "learning_rate": 0.0002,
      "loss": 0.4899,
      "step": 985
    },
    {
      "epoch": 0.9478219243657252,
      "grad_norm": 0.08913381397724152,
      "learning_rate": 0.0002,
      "loss": 0.5455,
      "step": 990
    },
    {
      "epoch": 0.9526089037817137,
      "grad_norm": 0.09054595977067947,
      "learning_rate": 0.0002,
      "loss": 0.528,
      "step": 995
    },
    {
      "epoch": 0.9573958831977023,
      "grad_norm": 0.0929536446928978,
      "learning_rate": 0.0002,
      "loss": 0.5595,
      "step": 1000
    },
    {
      "epoch": 0.9621828626136908,
      "grad_norm": 0.09117671847343445,
      "learning_rate": 0.0002,
      "loss": 0.5212,
      "step": 1005
    },
    {
      "epoch": 0.9669698420296793,
      "grad_norm": 0.09163827449083328,
      "learning_rate": 0.0002,
      "loss": 0.4587,
      "step": 1010
    },
    {
      "epoch": 0.9717568214456678,
      "grad_norm": 0.09541551768779755,
      "learning_rate": 0.0002,
      "loss": 0.5352,
      "step": 1015
    },
    {
      "epoch": 0.9765438008616563,
      "grad_norm": 0.09220823645591736,
      "learning_rate": 0.0002,
      "loss": 0.5599,
      "step": 1020
    },
    {
      "epoch": 0.9813307802776448,
      "grad_norm": 0.09834371507167816,
      "learning_rate": 0.0002,
      "loss": 0.5605,
      "step": 1025
    },
    {
      "epoch": 0.9861177596936334,
      "grad_norm": 0.08727829903364182,
      "learning_rate": 0.0002,
      "loss": 0.5427,
      "step": 1030
    },
    {
      "epoch": 0.9909047391096218,
      "grad_norm": 0.09128595143556595,
      "learning_rate": 0.0002,
      "loss": 0.574,
      "step": 1035
    },
    {
      "epoch": 0.9956917185256103,
      "grad_norm": 0.09627512097358704,
      "learning_rate": 0.0002,
      "loss": 0.4791,
      "step": 1040
    },
    {
      "epoch": 0.9995213020584012,
      "step": 1044,
      "total_flos": 2.304533815525294e+17,
      "train_loss": 0.5449674188862359,
      "train_runtime": 2251.699,
      "train_samples_per_second": 7.421,
      "train_steps_per_second": 0.464
    }
  ],
  "logging_steps": 5,
  "max_steps": 1044,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.304533815525294e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}