{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 733,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0068212824010914054,
      "grad_norm": 1.5700784921646118,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.8612,
      "num_tokens": 3753458.0,
      "step": 5
    },
    {
      "epoch": 0.013642564802182811,
      "grad_norm": 1.541254997253418,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.813,
      "num_tokens": 7657459.0,
      "step": 10
    },
    {
      "epoch": 0.020463847203274217,
      "grad_norm": 0.8007029294967651,
      "learning_rate": 1.891891891891892e-05,
      "loss": 0.7308,
      "num_tokens": 11351827.0,
      "step": 15
    },
    {
      "epoch": 0.027285129604365622,
      "grad_norm": 0.5904110074043274,
      "learning_rate": 2.5675675675675675e-05,
      "loss": 0.6861,
      "num_tokens": 15095356.0,
      "step": 20
    },
    {
      "epoch": 0.034106412005457026,
      "grad_norm": 0.5023650527000427,
      "learning_rate": 3.2432432432432436e-05,
      "loss": 0.6616,
      "num_tokens": 18878489.0,
      "step": 25
    },
    {
      "epoch": 0.040927694406548434,
      "grad_norm": 0.4876738488674164,
      "learning_rate": 3.918918918918919e-05,
      "loss": 0.6376,
      "num_tokens": 22607726.0,
      "step": 30
    },
    {
      "epoch": 0.047748976807639835,
      "grad_norm": 0.36882731318473816,
      "learning_rate": 4.594594594594595e-05,
      "loss": 0.6317,
      "num_tokens": 26596975.0,
      "step": 35
    },
    {
      "epoch": 0.054570259208731244,
      "grad_norm": 0.4269203245639801,
      "learning_rate": 4.999908316574644e-05,
      "loss": 0.5998,
      "num_tokens": 30372607.0,
      "step": 40
    },
    {
      "epoch": 0.061391541609822645,
      "grad_norm": 0.39412692189216614,
      "learning_rate": 4.998876963847189e-05,
      "loss": 0.6009,
      "num_tokens": 34180321.0,
      "step": 45
    },
    {
      "epoch": 0.06821282401091405,
      "grad_norm": 0.4157862067222595,
      "learning_rate": 4.996700181165029e-05,
      "loss": 0.6006,
      "num_tokens": 37904755.0,
      "step": 50
    },
    {
      "epoch": 0.07503410641200546,
      "grad_norm": 0.5112420916557312,
      "learning_rate": 4.993379077238036e-05,
      "loss": 0.6012,
      "num_tokens": 41764548.0,
      "step": 55
    },
    {
      "epoch": 0.08185538881309687,
      "grad_norm": 0.4662182927131653,
      "learning_rate": 4.9889153436180295e-05,
      "loss": 0.5892,
      "num_tokens": 45475394.0,
      "step": 60
    },
    {
      "epoch": 0.08867667121418826,
      "grad_norm": 0.47541704773902893,
      "learning_rate": 4.983311253837213e-05,
      "loss": 0.5928,
      "num_tokens": 49295807.0,
      "step": 65
    },
    {
      "epoch": 0.09549795361527967,
      "grad_norm": 0.4185464084148407,
      "learning_rate": 4.9765696622501846e-05,
      "loss": 0.5823,
      "num_tokens": 52931516.0,
      "step": 70
    },
    {
      "epoch": 0.10231923601637108,
      "grad_norm": 0.4303089380264282,
      "learning_rate": 4.968694002580118e-05,
      "loss": 0.5842,
      "num_tokens": 56824861.0,
      "step": 75
    },
    {
      "epoch": 0.10914051841746249,
      "grad_norm": 0.4935140013694763,
      "learning_rate": 4.959688286169851e-05,
      "loss": 0.5678,
      "num_tokens": 60559854.0,
      "step": 80
    },
    {
      "epoch": 0.11596180081855388,
      "grad_norm": 0.4861179292201996,
      "learning_rate": 4.9495570999387685e-05,
      "loss": 0.5616,
      "num_tokens": 64468301.0,
      "step": 85
    },
    {
      "epoch": 0.12278308321964529,
      "grad_norm": 0.5267655849456787,
      "learning_rate": 4.9383056040465276e-05,
      "loss": 0.5797,
      "num_tokens": 68324862.0,
      "step": 90
    },
    {
      "epoch": 0.1296043656207367,
      "grad_norm": 0.38909223675727844,
      "learning_rate": 4.925939529264815e-05,
      "loss": 0.5749,
      "num_tokens": 72145111.0,
      "step": 95
    },
    {
      "epoch": 0.1364256480218281,
      "grad_norm": 0.40435904264450073,
      "learning_rate": 4.9124651740584684e-05,
      "loss": 0.5612,
      "num_tokens": 76047530.0,
      "step": 100
    },
    {
      "epoch": 0.1432469304229195,
      "grad_norm": 0.44939741492271423,
      "learning_rate": 4.897889401377447e-05,
      "loss": 0.5631,
      "num_tokens": 80034081.0,
      "step": 105
    },
    {
      "epoch": 0.15006821282401092,
      "grad_norm": 0.373078316450119,
      "learning_rate": 4.882219635161306e-05,
      "loss": 0.5669,
      "num_tokens": 83777176.0,
      "step": 110
    },
    {
      "epoch": 0.15688949522510232,
      "grad_norm": 0.49139291048049927,
      "learning_rate": 4.865463856557922e-05,
      "loss": 0.5657,
      "num_tokens": 87560813.0,
      "step": 115
    },
    {
      "epoch": 0.16371077762619374,
      "grad_norm": 0.4161722958087921,
      "learning_rate": 4.847630599858426e-05,
      "loss": 0.5548,
      "num_tokens": 91406508.0,
      "step": 120
    },
    {
      "epoch": 0.17053206002728513,
      "grad_norm": 0.34772634506225586,
      "learning_rate": 4.8287289481503954e-05,
      "loss": 0.5617,
      "num_tokens": 95296652.0,
      "step": 125
    },
    {
      "epoch": 0.17735334242837653,
      "grad_norm": 0.40422406792640686,
      "learning_rate": 4.8087685286915276e-05,
      "loss": 0.557,
      "num_tokens": 99236540.0,
      "step": 130
    },
    {
      "epoch": 0.18417462482946795,
      "grad_norm": 0.38424786925315857,
      "learning_rate": 4.787759508006147e-05,
      "loss": 0.5566,
      "num_tokens": 103070715.0,
      "step": 135
    },
    {
      "epoch": 0.19099590723055934,
      "grad_norm": 0.47076845169067383,
      "learning_rate": 4.765712586707048e-05,
      "loss": 0.5696,
      "num_tokens": 106743213.0,
      "step": 140
    },
    {
      "epoch": 0.19781718963165076,
      "grad_norm": 0.48413094878196716,
      "learning_rate": 4.7426389940453065e-05,
      "loss": 0.542,
      "num_tokens": 110676628.0,
      "step": 145
    },
    {
      "epoch": 0.20463847203274216,
      "grad_norm": 0.46264445781707764,
      "learning_rate": 4.718550482190837e-05,
      "loss": 0.558,
      "num_tokens": 114351641.0,
      "step": 150
    },
    {
      "epoch": 0.21145975443383355,
      "grad_norm": 0.39284056425094604,
      "learning_rate": 4.6934593202466127e-05,
      "loss": 0.5426,
      "num_tokens": 118270253.0,
      "step": 155
    },
    {
      "epoch": 0.21828103683492497,
      "grad_norm": 0.4010249674320221,
      "learning_rate": 4.6673782879995896e-05,
      "loss": 0.5514,
      "num_tokens": 122130553.0,
      "step": 160
    },
    {
      "epoch": 0.22510231923601637,
      "grad_norm": 0.38185256719589233,
      "learning_rate": 4.640320669411526e-05,
      "loss": 0.5541,
      "num_tokens": 125907714.0,
      "step": 165
    },
    {
      "epoch": 0.23192360163710776,
      "grad_norm": 0.36932316422462463,
      "learning_rate": 4.612300245853004e-05,
      "loss": 0.5474,
      "num_tokens": 129778594.0,
      "step": 170
    },
    {
      "epoch": 0.23874488403819918,
      "grad_norm": 0.4994874894618988,
      "learning_rate": 4.5833312890841085e-05,
      "loss": 0.5622,
      "num_tokens": 133567859.0,
      "step": 175
    },
    {
      "epoch": 0.24556616643929058,
      "grad_norm": 0.4484744369983673,
      "learning_rate": 4.553428553985329e-05,
      "loss": 0.5418,
      "num_tokens": 137318470.0,
      "step": 180
    },
    {
      "epoch": 0.252387448840382,
      "grad_norm": 0.402942031621933,
      "learning_rate": 4.522607271042399e-05,
      "loss": 0.5368,
      "num_tokens": 140986549.0,
      "step": 185
    },
    {
      "epoch": 0.2592087312414734,
      "grad_norm": 0.5010215044021606,
      "learning_rate": 4.490883138588882e-05,
      "loss": 0.5482,
      "num_tokens": 144921526.0,
      "step": 190
    },
    {
      "epoch": 0.2660300136425648,
      "grad_norm": 0.39415615797042847,
      "learning_rate": 4.458272314810479e-05,
      "loss": 0.536,
      "num_tokens": 148719256.0,
      "step": 195
    },
    {
      "epoch": 0.2728512960436562,
      "grad_norm": 0.386960506439209,
      "learning_rate": 4.4247914095151086e-05,
      "loss": 0.546,
      "num_tokens": 152583124.0,
      "step": 200
    },
    {
      "epoch": 0.27967257844474763,
      "grad_norm": 0.4125616252422333,
      "learning_rate": 4.390457475672966e-05,
      "loss": 0.5395,
      "num_tokens": 156451358.0,
      "step": 205
    },
    {
      "epoch": 0.286493860845839,
      "grad_norm": 0.3309045732021332,
      "learning_rate": 4.35528800073086e-05,
      "loss": 0.541,
      "num_tokens": 160195441.0,
      "step": 210
    },
    {
      "epoch": 0.2933151432469304,
      "grad_norm": 0.3817555010318756,
      "learning_rate": 4.31930089770526e-05,
      "loss": 0.5443,
      "num_tokens": 164130734.0,
      "step": 215
    },
    {
      "epoch": 0.30013642564802184,
      "grad_norm": 0.39029499888420105,
      "learning_rate": 4.282514496058582e-05,
      "loss": 0.5238,
      "num_tokens": 167974083.0,
      "step": 220
    },
    {
      "epoch": 0.3069577080491132,
      "grad_norm": 0.33578798174858093,
      "learning_rate": 4.24494753236337e-05,
      "loss": 0.5365,
      "num_tokens": 171877159.0,
      "step": 225
    },
    {
      "epoch": 0.31377899045020463,
      "grad_norm": 0.3513656258583069,
      "learning_rate": 4.2066191407591125e-05,
      "loss": 0.5321,
      "num_tokens": 175825874.0,
      "step": 230
    },
    {
      "epoch": 0.32060027285129605,
      "grad_norm": 0.3408605456352234,
      "learning_rate": 4.1675488432065785e-05,
      "loss": 0.5244,
      "num_tokens": 179651504.0,
      "step": 235
    },
    {
      "epoch": 0.3274215552523875,
      "grad_norm": 0.30909132957458496,
      "learning_rate": 4.127756539544609e-05,
      "loss": 0.537,
      "num_tokens": 183474332.0,
      "step": 240
    },
    {
      "epoch": 0.33424283765347884,
      "grad_norm": 0.4393291175365448,
      "learning_rate": 4.087262497354452e-05,
      "loss": 0.5456,
      "num_tokens": 187421939.0,
      "step": 245
    },
    {
      "epoch": 0.34106412005457026,
      "grad_norm": 0.37006404995918274,
      "learning_rate": 4.046087341636789e-05,
      "loss": 0.528,
      "num_tokens": 191229072.0,
      "step": 250
    },
    {
      "epoch": 0.3478854024556617,
      "grad_norm": 0.32528236508369446,
      "learning_rate": 4.0042520443067176e-05,
      "loss": 0.5293,
      "num_tokens": 195078991.0,
      "step": 255
    },
    {
      "epoch": 0.35470668485675305,
      "grad_norm": 0.339620977640152,
      "learning_rate": 3.961777913512035e-05,
      "loss": 0.5183,
      "num_tokens": 198920961.0,
      "step": 260
    },
    {
      "epoch": 0.3615279672578445,
      "grad_norm": 0.32565462589263916,
      "learning_rate": 3.9186865827802724e-05,
      "loss": 0.5379,
      "num_tokens": 202602950.0,
      "step": 265
    },
    {
      "epoch": 0.3683492496589359,
      "grad_norm": 0.3410382866859436,
      "learning_rate": 3.875e-05,
      "loss": 0.5267,
      "num_tokens": 206455454.0,
      "step": 270
    },
    {
      "epoch": 0.37517053206002726,
      "grad_norm": 0.30947548151016235,
      "learning_rate": 3.830740416242014e-05,
      "loss": 0.5225,
      "num_tokens": 210274230.0,
      "step": 275
    },
    {
      "epoch": 0.3819918144611187,
      "grad_norm": 0.3249005079269409,
      "learning_rate": 3.7859303744261064e-05,
      "loss": 0.5284,
      "num_tokens": 213944648.0,
      "step": 280
    },
    {
      "epoch": 0.3888130968622101,
      "grad_norm": 0.3326890766620636,
      "learning_rate": 3.740592697839185e-05,
      "loss": 0.5331,
      "num_tokens": 217821264.0,
      "step": 285
    },
    {
      "epoch": 0.3956343792633015,
      "grad_norm": 0.30306893587112427,
      "learning_rate": 3.694750478510596e-05,
      "loss": 0.5286,
      "num_tokens": 221728874.0,
      "step": 290
    },
    {
      "epoch": 0.4024556616643929,
      "grad_norm": 0.2941177189350128,
      "learning_rate": 3.648427065450555e-05,
      "loss": 0.5198,
      "num_tokens": 225494536.0,
      "step": 295
    },
    {
      "epoch": 0.4092769440654843,
      "grad_norm": 0.30446290969848633,
      "learning_rate": 3.601646052757707e-05,
      "loss": 0.519,
      "num_tokens": 229370762.0,
      "step": 300
    },
    {
      "epoch": 0.41609822646657574,
      "grad_norm": 0.33618056774139404,
      "learning_rate": 3.55443126760184e-05,
      "loss": 0.5345,
      "num_tokens": 233272121.0,
      "step": 305
    },
    {
      "epoch": 0.4229195088676671,
      "grad_norm": 0.39119410514831543,
      "learning_rate": 3.506806758087894e-05,
      "loss": 0.5321,
      "num_tokens": 237043352.0,
      "step": 310
    },
    {
      "epoch": 0.4297407912687585,
      "grad_norm": 0.36198490858078003,
      "learning_rate": 3.458796781007437e-05,
      "loss": 0.5268,
      "num_tokens": 240757499.0,
      "step": 315
    },
    {
      "epoch": 0.43656207366984995,
      "grad_norm": 0.3167111277580261,
      "learning_rate": 3.410425789483854e-05,
      "loss": 0.5271,
      "num_tokens": 244605555.0,
      "step": 320
    },
    {
      "epoch": 0.4433833560709413,
      "grad_norm": 0.3152565360069275,
      "learning_rate": 3.3617184205175304e-05,
      "loss": 0.5336,
      "num_tokens": 248382993.0,
      "step": 325
    },
    {
      "epoch": 0.45020463847203274,
      "grad_norm": 0.3747156262397766,
      "learning_rate": 3.312699482437392e-05,
      "loss": 0.5208,
      "num_tokens": 252233466.0,
      "step": 330
    },
    {
      "epoch": 0.45702592087312416,
      "grad_norm": 0.36773014068603516,
      "learning_rate": 3.263393942265168e-05,
      "loss": 0.5275,
      "num_tokens": 256038440.0,
      "step": 335
    },
    {
      "epoch": 0.4638472032742155,
      "grad_norm": 0.2980627715587616,
      "learning_rate": 3.213826912998838e-05,
      "loss": 0.5199,
      "num_tokens": 260071254.0,
      "step": 340
    },
    {
      "epoch": 0.47066848567530695,
      "grad_norm": 0.31149786710739136,
      "learning_rate": 3.164023640821719e-05,
      "loss": 0.5132,
      "num_tokens": 263897078.0,
      "step": 345
    },
    {
      "epoch": 0.47748976807639837,
      "grad_norm": 0.30857953429222107,
      "learning_rate": 3.114009492243721e-05,
      "loss": 0.5217,
      "num_tokens": 267702266.0,
      "step": 350
    },
    {
      "epoch": 0.4843110504774898,
      "grad_norm": 0.303462952375412,
      "learning_rate": 3.063809941181321e-05,
      "loss": 0.5313,
      "num_tokens": 271571889.0,
      "step": 355
    },
    {
      "epoch": 0.49113233287858116,
      "grad_norm": 0.33175215125083923,
      "learning_rate": 3.0134505559828203e-05,
      "loss": 0.535,
      "num_tokens": 275444208.0,
      "step": 360
    },
    {
      "epoch": 0.4979536152796726,
      "grad_norm": 0.31040850281715393,
      "learning_rate": 2.9629569864055125e-05,
      "loss": 0.513,
      "num_tokens": 279090959.0,
      "step": 365
    },
    {
      "epoch": 0.504774897680764,
      "grad_norm": 0.3118685483932495,
      "learning_rate": 2.9123549505513868e-05,
      "loss": 0.515,
      "num_tokens": 283042351.0,
      "step": 370
    },
    {
      "epoch": 0.5115961800818554,
      "grad_norm": 0.28737205266952515,
      "learning_rate": 2.8616702217680134e-05,
      "loss": 0.523,
      "num_tokens": 286947035.0,
      "step": 375
    },
    {
      "epoch": 0.5184174624829468,
      "grad_norm": 0.32293662428855896,
      "learning_rate": 2.810928615521303e-05,
      "loss": 0.5097,
      "num_tokens": 290627149.0,
      "step": 380
    },
    {
      "epoch": 0.5252387448840382,
      "grad_norm": 0.30941659212112427,
      "learning_rate": 2.7601559762468022e-05,
      "loss": 0.5189,
      "num_tokens": 294445695.0,
      "step": 385
    },
    {
      "epoch": 0.5320600272851296,
      "grad_norm": 0.3308981955051422,
      "learning_rate": 2.7093781641862387e-05,
      "loss": 0.5215,
      "num_tokens": 298235939.0,
      "step": 390
    },
    {
      "epoch": 0.538881309686221,
      "grad_norm": 0.3184700608253479,
      "learning_rate": 2.658621042216021e-05,
      "loss": 0.5057,
      "num_tokens": 301940350.0,
      "step": 395
    },
    {
      "epoch": 0.5457025920873124,
      "grad_norm": 2.0989575386047363,
      "learning_rate": 2.6079104626743845e-05,
      "loss": 0.5267,
      "num_tokens": 305677252.0,
      "step": 400
    },
    {
      "epoch": 0.5525238744884038,
      "grad_norm": 0.37106770277023315,
      "learning_rate": 2.5572722541939113e-05,
      "loss": 0.5256,
      "num_tokens": 309492997.0,
      "step": 405
    },
    {
      "epoch": 0.5593451568894953,
      "grad_norm": 0.3112622797489166,
      "learning_rate": 2.5067322085461315e-05,
      "loss": 0.5105,
      "num_tokens": 313260754.0,
      "step": 410
    },
    {
      "epoch": 0.5661664392905866,
      "grad_norm": 0.4030674695968628,
      "learning_rate": 2.4563160675048846e-05,
      "loss": 0.5157,
      "num_tokens": 317054734.0,
      "step": 415
    },
    {
      "epoch": 0.572987721691678,
      "grad_norm": 0.3257318139076233,
      "learning_rate": 2.406049509735156e-05,
      "loss": 0.5153,
      "num_tokens": 320934035.0,
      "step": 420
    },
    {
      "epoch": 0.5798090040927695,
      "grad_norm": 0.3117997646331787,
      "learning_rate": 2.355958137714056e-05,
      "loss": 0.5108,
      "num_tokens": 324620533.0,
      "step": 425
    },
    {
      "epoch": 0.5866302864938608,
      "grad_norm": 0.3129447400569916,
      "learning_rate": 2.3060674646906004e-05,
      "loss": 0.5155,
      "num_tokens": 328343683.0,
      "step": 430
    },
    {
      "epoch": 0.5934515688949522,
      "grad_norm": 0.3214550316333771,
      "learning_rate": 2.2564029016909416e-05,
      "loss": 0.5048,
      "num_tokens": 332273995.0,
      "step": 435
    },
    {
      "epoch": 0.6002728512960437,
      "grad_norm": 0.2830764055252075,
      "learning_rate": 2.2069897445756627e-05,
      "loss": 0.5028,
      "num_tokens": 336096910.0,
      "step": 440
    },
    {
      "epoch": 0.607094133697135,
      "grad_norm": 0.2954827547073364,
      "learning_rate": 2.1578531611557322e-05,
      "loss": 0.5159,
      "num_tokens": 339854518.0,
      "step": 445
    },
    {
      "epoch": 0.6139154160982264,
      "grad_norm": 0.25289270281791687,
      "learning_rate": 2.109018178373675e-05,
      "loss": 0.5146,
      "num_tokens": 343729017.0,
      "step": 450
    },
    {
      "epoch": 0.6207366984993179,
      "grad_norm": 0.2954281270503998,
      "learning_rate": 2.0605096695564973e-05,
      "loss": 0.5182,
      "num_tokens": 347564883.0,
      "step": 455
    },
    {
      "epoch": 0.6275579809004093,
      "grad_norm": 0.264874666929245,
      "learning_rate": 2.0123523417468466e-05,
      "loss": 0.5115,
      "num_tokens": 351296309.0,
      "step": 460
    },
    {
      "epoch": 0.6343792633015006,
      "grad_norm": 0.2828667461872101,
      "learning_rate": 1.9645707231188742e-05,
      "loss": 0.5058,
      "num_tokens": 355112109.0,
      "step": 465
    },
    {
      "epoch": 0.6412005457025921,
      "grad_norm": 0.2687091529369354,
      "learning_rate": 1.9171891504851925e-05,
      "loss": 0.5245,
      "num_tokens": 358904864.0,
      "step": 470
    },
    {
      "epoch": 0.6480218281036835,
      "grad_norm": 0.2940763533115387,
      "learning_rate": 1.8702317569013094e-05,
      "loss": 0.5004,
      "num_tokens": 362651560.0,
      "step": 475
    },
    {
      "epoch": 0.654843110504775,
      "grad_norm": 0.2619578540325165,
      "learning_rate": 1.8237224593738327e-05,
      "loss": 0.5027,
      "num_tokens": 366319152.0,
      "step": 480
    },
    {
      "epoch": 0.6616643929058663,
      "grad_norm": 0.2464180737733841,
      "learning_rate": 1.7776849466787223e-05,
      "loss": 0.517,
      "num_tokens": 370176088.0,
      "step": 485
    },
    {
      "epoch": 0.6684856753069577,
      "grad_norm": 0.2550261616706848,
      "learning_rate": 1.7321426672957896e-05,
      "loss": 0.5025,
      "num_tokens": 374011109.0,
      "step": 490
    },
    {
      "epoch": 0.6753069577080492,
      "grad_norm": 0.2865135073661804,
      "learning_rate": 1.6871188174655787e-05,
      "loss": 0.4956,
      "num_tokens": 377769452.0,
      "step": 495
    },
    {
      "epoch": 0.6821282401091405,
      "grad_norm": 0.25042206048965454,
      "learning_rate": 1.6426363293747334e-05,
      "loss": 0.5,
      "num_tokens": 381536770.0,
      "step": 500
    },
    {
      "epoch": 0.6889495225102319,
      "grad_norm": 0.26310259103775024,
      "learning_rate": 1.598717859475846e-05,
      "loss": 0.5086,
      "num_tokens": 385264947.0,
      "step": 505
    },
    {
      "epoch": 0.6957708049113234,
      "grad_norm": 0.26373496651649475,
      "learning_rate": 1.5553857769477553e-05,
      "loss": 0.5055,
      "num_tokens": 389008667.0,
      "step": 510
    },
    {
      "epoch": 0.7025920873124147,
      "grad_norm": 0.2504028379917145,
      "learning_rate": 1.5126621523021518e-05,
      "loss": 0.51,
      "num_tokens": 392845122.0,
      "step": 515
    },
    {
      "epoch": 0.7094133697135061,
      "grad_norm": 0.3016691505908966,
      "learning_rate": 1.4705687461423209e-05,
      "loss": 0.5223,
      "num_tokens": 396569410.0,
      "step": 520
    },
    {
      "epoch": 0.7162346521145976,
      "grad_norm": 0.26355814933776855,
      "learning_rate": 1.4291269980797139e-05,
      "loss": 0.5065,
      "num_tokens": 400328978.0,
      "step": 525
    },
    {
      "epoch": 0.723055934515689,
      "grad_norm": 0.258340448141098,
      "learning_rate": 1.3883580158140291e-05,
      "loss": 0.5004,
      "num_tokens": 404085025.0,
      "step": 530
    },
    {
      "epoch": 0.7298772169167803,
      "grad_norm": 0.23762258887290955,
      "learning_rate": 1.3482825643823293e-05,
      "loss": 0.5061,
      "num_tokens": 407976499.0,
      "step": 535
    },
    {
      "epoch": 0.7366984993178718,
      "grad_norm": 0.24250030517578125,
      "learning_rate": 1.3089210555827086e-05,
      "loss": 0.512,
      "num_tokens": 411774021.0,
      "step": 540
    },
    {
      "epoch": 0.7435197817189632,
      "grad_norm": 0.23150943219661713,
      "learning_rate": 1.270293537577855e-05,
      "loss": 0.5147,
      "num_tokens": 415754417.0,
      "step": 545
    },
    {
      "epoch": 0.7503410641200545,
      "grad_norm": 0.24009953439235687,
      "learning_rate": 1.232419684683844e-05,
      "loss": 0.4995,
      "num_tokens": 419428701.0,
      "step": 550
    },
    {
      "epoch": 0.757162346521146,
      "grad_norm": 0.24892768263816833,
      "learning_rate": 1.1953187873493303e-05,
      "loss": 0.5001,
      "num_tokens": 423056747.0,
      "step": 555
    },
    {
      "epoch": 0.7639836289222374,
      "grad_norm": 0.2480500489473343,
      "learning_rate": 1.1590097423302684e-05,
      "loss": 0.496,
      "num_tokens": 426771236.0,
      "step": 560
    },
    {
      "epoch": 0.7708049113233287,
      "grad_norm": 0.23765107989311218,
      "learning_rate": 1.1235110430651421e-05,
      "loss": 0.4959,
      "num_tokens": 430648058.0,
      "step": 565
    },
    {
      "epoch": 0.7776261937244202,
      "grad_norm": 0.25531235337257385,
      "learning_rate": 1.0888407702556284e-05,
      "loss": 0.4998,
      "num_tokens": 434432023.0,
      "step": 570
    },
    {
      "epoch": 0.7844474761255116,
      "grad_norm": 0.262312114238739,
      "learning_rate": 1.0550165826574766e-05,
      "loss": 0.4995,
      "num_tokens": 438355231.0,
      "step": 575
    },
    {
      "epoch": 0.791268758526603,
      "grad_norm": 0.25291720032691956,
      "learning_rate": 1.0220557080862985e-05,
      "loss": 0.5148,
      "num_tokens": 442388385.0,
      "step": 580
    },
    {
      "epoch": 0.7980900409276944,
      "grad_norm": 0.22738206386566162,
      "learning_rate": 9.899749346428556e-06,
      "loss": 0.502,
      "num_tokens": 446189045.0,
      "step": 585
    },
    {
      "epoch": 0.8049113233287858,
      "grad_norm": 0.2262069582939148,
      "learning_rate": 9.587906021623016e-06,
      "loss": 0.5161,
      "num_tokens": 450018716.0,
      "step": 590
    },
    {
      "epoch": 0.8117326057298773,
      "grad_norm": 0.2656482458114624,
      "learning_rate": 9.28518593891749e-06,
      "loss": 0.5013,
      "num_tokens": 453809691.0,
      "step": 595
    },
    {
      "epoch": 0.8185538881309686,
      "grad_norm": 0.2433101087808609,
      "learning_rate": 8.99174328400385e-06,
      "loss": 0.4996,
      "num_tokens": 457645977.0,
      "step": 600
    },
    {
      "epoch": 0.82537517053206,
      "grad_norm": 0.25572413206100464,
      "learning_rate": 8.707727517262697e-06,
      "loss": 0.5049,
      "num_tokens": 461370305.0,
      "step": 605
    },
    {
      "epoch": 0.8321964529331515,
      "grad_norm": 0.23688948154449463,
      "learning_rate": 8.433283297638053e-06,
      "loss": 0.4992,
      "num_tokens": 465282670.0,
      "step": 610
    },
    {
      "epoch": 0.8390177353342428,
      "grad_norm": 0.23922283947467804,
      "learning_rate": 8.168550408957632e-06,
      "loss": 0.4969,
      "num_tokens": 469094631.0,
      "step": 615
    },
    {
      "epoch": 0.8458390177353342,
      "grad_norm": 0.25452542304992676,
      "learning_rate": 7.91366368873613e-06,
      "loss": 0.4944,
      "num_tokens": 472868071.0,
      "step": 620
    },
    {
      "epoch": 0.8526603001364257,
      "grad_norm": 0.24521248042583466,
      "learning_rate": 7.66875295949791e-06,
      "loss": 0.5104,
      "num_tokens": 476693164.0,
      "step": 625
    },
    {
      "epoch": 0.859481582537517,
      "grad_norm": 0.2180357724428177,
      "learning_rate": 7.4339429626539e-06,
      "loss": 0.5101,
      "num_tokens": 480634992.0,
      "step": 630
    },
    {
      "epoch": 0.8663028649386084,
      "grad_norm": 0.25706538558006287,
      "learning_rate": 7.2093532949665715e-06,
      "loss": 0.508,
      "num_tokens": 484452349.0,
      "step": 635
    },
    {
      "epoch": 0.8731241473396999,
      "grad_norm": 0.22597377002239227,
      "learning_rate": 6.995098347635173e-06,
      "loss": 0.4933,
      "num_tokens": 488334317.0,
      "step": 640
    },
    {
      "epoch": 0.8799454297407913,
      "grad_norm": 0.23853003978729248,
      "learning_rate": 6.791287248032431e-06,
      "loss": 0.4965,
      "num_tokens": 492162119.0,
      "step": 645
    },
    {
      "epoch": 0.8867667121418826,
      "grad_norm": 0.2505284547805786,
      "learning_rate": 6.598023804122194e-06,
      "loss": 0.5037,
      "num_tokens": 496169094.0,
      "step": 650
    },
    {
      "epoch": 0.8935879945429741,
      "grad_norm": 0.22088280320167542,
      "learning_rate": 6.415406451586528e-06,
      "loss": 0.4993,
      "num_tokens": 500122283.0,
      "step": 655
    },
    {
      "epoch": 0.9004092769440655,
      "grad_norm": 0.21783269941806793,
      "learning_rate": 6.243528203689025e-06,
      "loss": 0.5031,
      "num_tokens": 504062446.0,
      "step": 660
    },
    {
      "epoch": 0.9072305593451568,
      "grad_norm": 0.22754983603954315,
      "learning_rate": 6.0824766039e-06,
      "loss": 0.4993,
      "num_tokens": 507853633.0,
      "step": 665
    },
    {
      "epoch": 0.9140518417462483,
      "grad_norm": 0.21411247551441193,
      "learning_rate": 5.932333681307571e-06,
      "loss": 0.5061,
      "num_tokens": 511714869.0,
      "step": 670
    },
    {
      "epoch": 0.9208731241473397,
      "grad_norm": 0.21759825944900513,
      "learning_rate": 5.793175908837471e-06,
      "loss": 0.4966,
      "num_tokens": 515451192.0,
      "step": 675
    },
    {
      "epoch": 0.927694406548431,
      "grad_norm": 0.21772339940071106,
      "learning_rate": 5.665074164302742e-06,
      "loss": 0.5063,
      "num_tokens": 519195745.0,
      "step": 680
    },
    {
      "epoch": 0.9345156889495225,
      "grad_norm": 0.20628990232944489,
      "learning_rate": 5.548093694303275e-06,
      "loss": 0.4918,
      "num_tokens": 523017567.0,
      "step": 685
    },
    {
      "epoch": 0.9413369713506139,
      "grad_norm": 0.23247572779655457,
      "learning_rate": 5.442294080993446e-06,
      "loss": 0.5059,
      "num_tokens": 526884969.0,
      "step": 690
    },
    {
      "epoch": 0.9481582537517054,
      "grad_norm": 0.21672718226909637,
      "learning_rate": 5.347729211734919e-06,
      "loss": 0.5033,
      "num_tokens": 530678785.0,
      "step": 695
    },
    {
      "epoch": 0.9549795361527967,
      "grad_norm": 0.21295787394046783,
      "learning_rate": 5.264447251649954e-06,
      "loss": 0.5057,
      "num_tokens": 534460009.0,
      "step": 700
    },
    {
      "epoch": 0.9618008185538881,
      "grad_norm": 0.21965418756008148,
      "learning_rate": 5.192490619089267e-06,
      "loss": 0.4899,
      "num_tokens": 538338585.0,
      "step": 705
    },
    {
      "epoch": 0.9686221009549796,
      "grad_norm": 0.21933406591415405,
      "learning_rate": 5.1318959640269095e-06,
      "loss": 0.5005,
      "num_tokens": 542019550.0,
      "step": 710
    },
    {
      "epoch": 0.975443383356071,
      "grad_norm": 0.2290937751531601,
      "learning_rate": 5.082694149393189e-06,
      "loss": 0.5113,
      "num_tokens": 545767802.0,
      "step": 715
    },
    {
      "epoch": 0.9822646657571623,
      "grad_norm": 0.23024672269821167,
      "learning_rate": 5.044910235355121e-06,
      "loss": 0.4973,
      "num_tokens": 549561878.0,
      "step": 720
    },
    {
      "epoch": 0.9890859481582538,
      "grad_norm": 0.20155958831310272,
      "learning_rate": 5.0185634665524255e-06,
      "loss": 0.4933,
      "num_tokens": 553402412.0,
      "step": 725
    },
    {
      "epoch": 0.9959072305593452,
      "grad_norm": 0.20187729597091675,
      "learning_rate": 5.003667262295572e-06,
      "loss": 0.5014,
      "num_tokens": 557174057.0,
      "step": 730
    },
    {
      "epoch": 1.0,
      "num_tokens": 559480552.0,
      "step": 733,
      "total_flos": 1.0371853292601868e+19,
      "train_loss": 0.5348884052664327,
      "train_runtime": 11645.0887,
      "train_samples_per_second": 8.049,
      "train_steps_per_second": 0.063
    }
  ],
  "logging_steps": 5,
  "max_steps": 733,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0371853292601868e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}