{
  "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": 1.5664408206939697,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.8612,
      "num_tokens": 3753458.0,
      "step": 5
    },
    {
      "epoch": 0.013642564802182811,
      "grad_norm": 1.5331162214279175,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.8129,
      "num_tokens": 7657459.0,
      "step": 10
    },
    {
      "epoch": 0.020463847203274217,
      "grad_norm": 0.7885063886642456,
      "learning_rate": 1.891891891891892e-05,
      "loss": 0.7307,
      "num_tokens": 11351827.0,
      "step": 15
    },
    {
      "epoch": 0.027285129604365622,
      "grad_norm": 0.5782262682914734,
      "learning_rate": 2.5675675675675675e-05,
      "loss": 0.686,
      "num_tokens": 15095356.0,
      "step": 20
    },
    {
      "epoch": 0.034106412005457026,
      "grad_norm": 0.49164527654647827,
      "learning_rate": 3.2432432432432436e-05,
      "loss": 0.6616,
      "num_tokens": 18878489.0,
      "step": 25
    },
    {
      "epoch": 0.040927694406548434,
      "grad_norm": 0.47542551159858704,
      "learning_rate": 3.918918918918919e-05,
      "loss": 0.6376,
      "num_tokens": 22607726.0,
      "step": 30
    },
    {
      "epoch": 0.047748976807639835,
      "grad_norm": 0.3627755045890808,
      "learning_rate": 4.594594594594595e-05,
      "loss": 0.6316,
      "num_tokens": 26596975.0,
      "step": 35
    },
    {
      "epoch": 0.054570259208731244,
      "grad_norm": 0.4120884835720062,
      "learning_rate": 4.999908316574644e-05,
      "loss": 0.5997,
      "num_tokens": 30372607.0,
      "step": 40
    },
    {
      "epoch": 0.061391541609822645,
      "grad_norm": 0.3788425028324127,
      "learning_rate": 4.998876963847189e-05,
      "loss": 0.6009,
      "num_tokens": 34180321.0,
      "step": 45
    },
    {
      "epoch": 0.06821282401091405,
      "grad_norm": 0.3772900700569153,
      "learning_rate": 4.996700181165029e-05,
      "loss": 0.6005,
      "num_tokens": 37904755.0,
      "step": 50
    },
    {
      "epoch": 0.07503410641200546,
      "grad_norm": 0.42741668224334717,
      "learning_rate": 4.993379077238036e-05,
      "loss": 0.601,
      "num_tokens": 41764548.0,
      "step": 55
    },
    {
      "epoch": 0.08185538881309687,
      "grad_norm": 0.4014478027820587,
      "learning_rate": 4.9889153436180295e-05,
      "loss": 0.5889,
      "num_tokens": 45475394.0,
      "step": 60
    },
    {
      "epoch": 0.08867667121418826,
      "grad_norm": 0.41353562474250793,
      "learning_rate": 4.983311253837213e-05,
      "loss": 0.5926,
      "num_tokens": 49295807.0,
      "step": 65
    },
    {
      "epoch": 0.09549795361527967,
      "grad_norm": 0.34759485721588135,
      "learning_rate": 4.9765696622501846e-05,
      "loss": 0.582,
      "num_tokens": 52931516.0,
      "step": 70
    },
    {
      "epoch": 0.10231923601637108,
      "grad_norm": 0.383974552154541,
      "learning_rate": 4.968694002580118e-05,
      "loss": 0.5839,
      "num_tokens": 56824861.0,
      "step": 75
    },
    {
      "epoch": 0.10914051841746249,
      "grad_norm": 0.4282758831977844,
      "learning_rate": 4.959688286169851e-05,
      "loss": 0.5676,
      "num_tokens": 60559854.0,
      "step": 80
    },
    {
      "epoch": 0.11596180081855388,
      "grad_norm": 0.4353692829608917,
      "learning_rate": 4.9495570999387685e-05,
      "loss": 0.5613,
      "num_tokens": 64468301.0,
      "step": 85
    },
    {
      "epoch": 0.12278308321964529,
      "grad_norm": 0.4118047058582306,
      "learning_rate": 4.9383056040465276e-05,
      "loss": 0.5793,
      "num_tokens": 68324862.0,
      "step": 90
    },
    {
      "epoch": 0.1296043656207367,
      "grad_norm": 0.36806777119636536,
      "learning_rate": 4.925939529264815e-05,
      "loss": 0.5747,
      "num_tokens": 72145111.0,
      "step": 95
    },
    {
      "epoch": 0.1364256480218281,
      "grad_norm": 0.3960418403148651,
      "learning_rate": 4.9124651740584684e-05,
      "loss": 0.561,
      "num_tokens": 76047530.0,
      "step": 100
    },
    {
      "epoch": 0.1432469304229195,
      "grad_norm": 0.39603474736213684,
      "learning_rate": 4.897889401377447e-05,
      "loss": 0.5629,
      "num_tokens": 80034081.0,
      "step": 105
    },
    {
      "epoch": 0.15006821282401092,
      "grad_norm": 0.34311339259147644,
      "learning_rate": 4.882219635161306e-05,
      "loss": 0.5667,
      "num_tokens": 83777176.0,
      "step": 110
    },
    {
      "epoch": 0.15688949522510232,
      "grad_norm": 0.4239673614501953,
      "learning_rate": 4.865463856557922e-05,
      "loss": 0.5656,
      "num_tokens": 87560813.0,
      "step": 115
    },
    {
      "epoch": 0.16371077762619374,
      "grad_norm": 0.37248337268829346,
      "learning_rate": 4.847630599858426e-05,
      "loss": 0.5547,
      "num_tokens": 91406508.0,
      "step": 120
    },
    {
      "epoch": 0.17053206002728513,
      "grad_norm": 0.3312360346317291,
      "learning_rate": 4.8287289481503954e-05,
      "loss": 0.5616,
      "num_tokens": 95296652.0,
      "step": 125
    },
    {
      "epoch": 0.17735334242837653,
      "grad_norm": 0.3752099871635437,
      "learning_rate": 4.8087685286915276e-05,
      "loss": 0.5569,
      "num_tokens": 99236540.0,
      "step": 130
    },
    {
      "epoch": 0.18417462482946795,
      "grad_norm": 0.3752726912498474,
      "learning_rate": 4.787759508006147e-05,
      "loss": 0.5565,
      "num_tokens": 103070715.0,
      "step": 135
    },
    {
      "epoch": 0.19099590723055934,
      "grad_norm": 0.40951457619667053,
      "learning_rate": 4.765712586707048e-05,
      "loss": 0.5694,
      "num_tokens": 106743213.0,
      "step": 140
    },
    {
      "epoch": 0.19781718963165076,
      "grad_norm": 0.39596056938171387,
      "learning_rate": 4.7426389940453065e-05,
      "loss": 0.5418,
      "num_tokens": 110676628.0,
      "step": 145
    },
    {
      "epoch": 0.20463847203274216,
      "grad_norm": 0.4065423309803009,
      "learning_rate": 4.718550482190837e-05,
      "loss": 0.5578,
      "num_tokens": 114351641.0,
      "step": 150
    },
    {
      "epoch": 0.21145975443383355,
      "grad_norm": 0.3387225568294525,
      "learning_rate": 4.6934593202466127e-05,
      "loss": 0.5424,
      "num_tokens": 118270253.0,
      "step": 155
    },
    {
      "epoch": 0.21828103683492497,
      "grad_norm": 0.3324713110923767,
      "learning_rate": 4.6673782879995896e-05,
      "loss": 0.5511,
      "num_tokens": 122130553.0,
      "step": 160
    },
    {
      "epoch": 0.22510231923601637,
      "grad_norm": 0.34876254200935364,
      "learning_rate": 4.640320669411526e-05,
      "loss": 0.5539,
      "num_tokens": 125907714.0,
      "step": 165
    },
    {
      "epoch": 0.23192360163710776,
      "grad_norm": 0.3520093858242035,
      "learning_rate": 4.612300245853004e-05,
      "loss": 0.5473,
      "num_tokens": 129778594.0,
      "step": 170
    },
    {
      "epoch": 0.23874488403819918,
      "grad_norm": 0.4421618580818176,
      "learning_rate": 4.5833312890841085e-05,
      "loss": 0.562,
      "num_tokens": 133567859.0,
      "step": 175
    },
    {
      "epoch": 0.24556616643929058,
      "grad_norm": 0.3951200544834137,
      "learning_rate": 4.553428553985329e-05,
      "loss": 0.5416,
      "num_tokens": 137318470.0,
      "step": 180
    },
    {
      "epoch": 0.252387448840382,
      "grad_norm": 0.37818825244903564,
      "learning_rate": 4.522607271042399e-05,
      "loss": 0.5366,
      "num_tokens": 140986549.0,
      "step": 185
    },
    {
      "epoch": 0.2592087312414734,
      "grad_norm": 0.43682247400283813,
      "learning_rate": 4.490883138588882e-05,
      "loss": 0.5479,
      "num_tokens": 144921526.0,
      "step": 190
    },
    {
      "epoch": 0.2660300136425648,
      "grad_norm": 0.32613101601600647,
      "learning_rate": 4.458272314810479e-05,
      "loss": 0.5358,
      "num_tokens": 148719256.0,
      "step": 195
    },
    {
      "epoch": 0.2728512960436562,
      "grad_norm": 0.31748515367507935,
      "learning_rate": 4.4247914095151086e-05,
      "loss": 0.5457,
      "num_tokens": 152583124.0,
      "step": 200
    },
    {
      "epoch": 0.27967257844474763,
      "grad_norm": 0.3875013589859009,
      "learning_rate": 4.390457475672966e-05,
      "loss": 0.5393,
      "num_tokens": 156451358.0,
      "step": 205
    },
    {
      "epoch": 0.286493860845839,
      "grad_norm": 0.33466753363609314,
      "learning_rate": 4.35528800073086e-05,
      "loss": 0.5408,
      "num_tokens": 160195441.0,
      "step": 210
    },
    {
      "epoch": 0.2933151432469304,
      "grad_norm": 0.3655596077442169,
      "learning_rate": 4.31930089770526e-05,
      "loss": 0.5442,
      "num_tokens": 164130734.0,
      "step": 215
    },
    {
      "epoch": 0.30013642564802184,
      "grad_norm": 0.35074111819267273,
      "learning_rate": 4.282514496058582e-05,
      "loss": 0.5236,
      "num_tokens": 167974083.0,
      "step": 220
    },
    {
      "epoch": 0.3069577080491132,
      "grad_norm": 0.3069048225879669,
      "learning_rate": 4.24494753236337e-05,
      "loss": 0.5363,
      "num_tokens": 171877159.0,
      "step": 225
    },
    {
      "epoch": 0.31377899045020463,
      "grad_norm": 0.3370104134082794,
      "learning_rate": 4.2066191407591125e-05,
      "loss": 0.5319,
      "num_tokens": 175825874.0,
      "step": 230
    },
    {
      "epoch": 0.32060027285129605,
      "grad_norm": 0.30355367064476013,
      "learning_rate": 4.1675488432065785e-05,
      "loss": 0.5242,
      "num_tokens": 179651504.0,
      "step": 235
    },
    {
      "epoch": 0.3274215552523875,
      "grad_norm": 0.29714441299438477,
      "learning_rate": 4.127756539544609e-05,
      "loss": 0.5368,
      "num_tokens": 183474332.0,
      "step": 240
    },
    {
      "epoch": 0.33424283765347884,
      "grad_norm": 0.34279632568359375,
      "learning_rate": 4.087262497354452e-05,
      "loss": 0.5453,
      "num_tokens": 187421939.0,
      "step": 245
    },
    {
      "epoch": 0.34106412005457026,
      "grad_norm": 0.3006781339645386,
      "learning_rate": 4.046087341636789e-05,
      "loss": 0.5278,
      "num_tokens": 191229072.0,
      "step": 250
    },
    {
      "epoch": 0.3478854024556617,
      "grad_norm": 0.30111509561538696,
      "learning_rate": 4.0042520443067176e-05,
      "loss": 0.529,
      "num_tokens": 195078991.0,
      "step": 255
    },
    {
      "epoch": 0.35470668485675305,
      "grad_norm": 0.3227461576461792,
      "learning_rate": 3.961777913512035e-05,
      "loss": 0.5181,
      "num_tokens": 198920961.0,
      "step": 260
    },
    {
      "epoch": 0.3615279672578445,
      "grad_norm": 0.30752789974212646,
      "learning_rate": 3.9186865827802724e-05,
      "loss": 0.5377,
      "num_tokens": 202602950.0,
      "step": 265
    },
    {
      "epoch": 0.3683492496589359,
      "grad_norm": 0.32034164667129517,
      "learning_rate": 3.875e-05,
      "loss": 0.5265,
      "num_tokens": 206455454.0,
      "step": 270
    },
    {
      "epoch": 0.37517053206002726,
      "grad_norm": 0.28475409746170044,
      "learning_rate": 3.830740416242014e-05,
      "loss": 0.5223,
      "num_tokens": 210274230.0,
      "step": 275
    },
    {
      "epoch": 0.3819918144611187,
      "grad_norm": 0.30314069986343384,
      "learning_rate": 3.7859303744261064e-05,
      "loss": 0.5281,
      "num_tokens": 213944648.0,
      "step": 280
    },
    {
      "epoch": 0.3888130968622101,
      "grad_norm": 0.28140079975128174,
      "learning_rate": 3.740592697839185e-05,
      "loss": 0.5328,
      "num_tokens": 217821264.0,
      "step": 285
    },
    {
      "epoch": 0.3956343792633015,
      "grad_norm": 0.26929807662963867,
      "learning_rate": 3.694750478510596e-05,
      "loss": 0.5284,
      "num_tokens": 221728874.0,
      "step": 290
    },
    {
      "epoch": 0.4024556616643929,
      "grad_norm": 0.26649391651153564,
      "learning_rate": 3.648427065450555e-05,
      "loss": 0.5196,
      "num_tokens": 225494536.0,
      "step": 295
    },
    {
      "epoch": 0.4092769440654843,
      "grad_norm": 0.29355040192604065,
      "learning_rate": 3.601646052757707e-05,
      "loss": 0.5188,
      "num_tokens": 229370762.0,
      "step": 300
    },
    {
      "epoch": 0.41609822646657574,
      "grad_norm": 0.3135109543800354,
      "learning_rate": 3.55443126760184e-05,
      "loss": 0.5343,
      "num_tokens": 233272121.0,
      "step": 305
    },
    {
      "epoch": 0.4229195088676671,
      "grad_norm": 0.3388509154319763,
      "learning_rate": 3.506806758087894e-05,
      "loss": 0.5319,
      "num_tokens": 237043352.0,
      "step": 310
    },
    {
      "epoch": 0.4297407912687585,
      "grad_norm": 0.30362528562545776,
      "learning_rate": 3.458796781007437e-05,
      "loss": 0.5266,
      "num_tokens": 240757499.0,
      "step": 315
    },
    {
      "epoch": 0.43656207366984995,
      "grad_norm": 0.28180354833602905,
      "learning_rate": 3.410425789483854e-05,
      "loss": 0.527,
      "num_tokens": 244605555.0,
      "step": 320
    },
    {
      "epoch": 0.4433833560709413,
      "grad_norm": 0.28672918677330017,
      "learning_rate": 3.3617184205175304e-05,
      "loss": 0.5334,
      "num_tokens": 248382993.0,
      "step": 325
    },
    {
      "epoch": 0.45020463847203274,
      "grad_norm": 0.33284738659858704,
      "learning_rate": 3.312699482437392e-05,
      "loss": 0.5206,
      "num_tokens": 252233466.0,
      "step": 330
    },
    {
      "epoch": 0.45702592087312416,
      "grad_norm": 0.28790685534477234,
      "learning_rate": 3.263393942265168e-05,
      "loss": 0.5273,
      "num_tokens": 256038440.0,
      "step": 335
    },
    {
      "epoch": 0.4638472032742155,
      "grad_norm": 0.25374555587768555,
      "learning_rate": 3.213826912998838e-05,
      "loss": 0.5197,
      "num_tokens": 260071254.0,
      "step": 340
    },
    {
      "epoch": 0.47066848567530695,
      "grad_norm": 0.26900210976600647,
      "learning_rate": 3.164023640821719e-05,
      "loss": 0.513,
      "num_tokens": 263897078.0,
      "step": 345
    },
    {
      "epoch": 0.47748976807639837,
      "grad_norm": 0.27621471881866455,
      "learning_rate": 3.114009492243721e-05,
      "loss": 0.5214,
      "num_tokens": 267702266.0,
      "step": 350
    },
    {
      "epoch": 0.4843110504774898,
      "grad_norm": 0.28301048278808594,
      "learning_rate": 3.063809941181321e-05,
      "loss": 0.531,
      "num_tokens": 271571889.0,
      "step": 355
    },
    {
      "epoch": 0.49113233287858116,
      "grad_norm": 0.28320661187171936,
      "learning_rate": 3.0134505559828203e-05,
      "loss": 0.5348,
      "num_tokens": 275444208.0,
      "step": 360
    },
    {
      "epoch": 0.4979536152796726,
      "grad_norm": 0.2856563925743103,
      "learning_rate": 2.9629569864055125e-05,
      "loss": 0.5128,
      "num_tokens": 279090959.0,
      "step": 365
    },
    {
      "epoch": 0.504774897680764,
      "grad_norm": 0.2746957540512085,
      "learning_rate": 2.9123549505513868e-05,
      "loss": 0.5148,
      "num_tokens": 283042351.0,
      "step": 370
    },
    {
      "epoch": 0.5115961800818554,
      "grad_norm": 0.27719607949256897,
      "learning_rate": 2.8616702217680134e-05,
      "loss": 0.5228,
      "num_tokens": 286947035.0,
      "step": 375
    },
    {
      "epoch": 0.5184174624829468,
      "grad_norm": 0.27276405692100525,
      "learning_rate": 2.810928615521303e-05,
      "loss": 0.5095,
      "num_tokens": 290627149.0,
      "step": 380
    },
    {
      "epoch": 0.5252387448840382,
      "grad_norm": 0.27591395378112793,
      "learning_rate": 2.7601559762468022e-05,
      "loss": 0.5187,
      "num_tokens": 294445695.0,
      "step": 385
    },
    {
      "epoch": 0.5320600272851296,
      "grad_norm": 0.27681204676628113,
      "learning_rate": 2.7093781641862387e-05,
      "loss": 0.5212,
      "num_tokens": 298235939.0,
      "step": 390
    },
    {
      "epoch": 0.538881309686221,
      "grad_norm": 0.2667984366416931,
      "learning_rate": 2.658621042216021e-05,
      "loss": 0.5054,
      "num_tokens": 301940350.0,
      "step": 395
    },
    {
      "epoch": 0.5457025920873124,
      "grad_norm": 0.6714840531349182,
      "learning_rate": 2.6079104626743845e-05,
      "loss": 0.5256,
      "num_tokens": 305677252.0,
      "step": 400
    },
    {
      "epoch": 0.5525238744884038,
      "grad_norm": 0.2727600634098053,
      "learning_rate": 2.5572722541939113e-05,
      "loss": 0.5248,
      "num_tokens": 309492997.0,
      "step": 405
    },
    {
      "epoch": 0.5593451568894953,
      "grad_norm": 0.28910964727401733,
      "learning_rate": 2.5067322085461315e-05,
      "loss": 0.5102,
      "num_tokens": 313260754.0,
      "step": 410
    },
    {
      "epoch": 0.5661664392905866,
      "grad_norm": 0.30671924352645874,
      "learning_rate": 2.4563160675048846e-05,
      "loss": 0.5153,
      "num_tokens": 317054734.0,
      "step": 415
    },
    {
      "epoch": 0.572987721691678,
      "grad_norm": 0.2649187743663788,
      "learning_rate": 2.406049509735156e-05,
      "loss": 0.5151,
      "num_tokens": 320934035.0,
      "step": 420
    },
    {
      "epoch": 0.5798090040927695,
      "grad_norm": 0.28437790274620056,
      "learning_rate": 2.355958137714056e-05,
      "loss": 0.5106,
      "num_tokens": 324620533.0,
      "step": 425
    },
    {
      "epoch": 0.5866302864938608,
      "grad_norm": 0.2717227041721344,
      "learning_rate": 2.3060674646906004e-05,
      "loss": 0.5152,
      "num_tokens": 328343683.0,
      "step": 430
    },
    {
      "epoch": 0.5934515688949522,
      "grad_norm": 0.3002876341342926,
      "learning_rate": 2.2564029016909416e-05,
      "loss": 0.5046,
      "num_tokens": 332273995.0,
      "step": 435
    },
    {
      "epoch": 0.6002728512960437,
      "grad_norm": 0.26823899149894714,
      "learning_rate": 2.2069897445756627e-05,
      "loss": 0.5026,
      "num_tokens": 336096910.0,
      "step": 440
    },
    {
      "epoch": 0.607094133697135,
      "grad_norm": 0.26657503843307495,
      "learning_rate": 2.1578531611557322e-05,
      "loss": 0.5156,
      "num_tokens": 339854518.0,
      "step": 445
    },
    {
      "epoch": 0.6139154160982264,
      "grad_norm": 0.2396160513162613,
      "learning_rate": 2.109018178373675e-05,
      "loss": 0.5144,
      "num_tokens": 343729017.0,
      "step": 450
    },
    {
      "epoch": 0.6207366984993179,
      "grad_norm": 0.25998055934906006,
      "learning_rate": 2.0605096695564973e-05,
      "loss": 0.5179,
      "num_tokens": 347564883.0,
      "step": 455
    },
    {
      "epoch": 0.6275579809004093,
      "grad_norm": 0.2405814677476883,
      "learning_rate": 2.0123523417468466e-05,
      "loss": 0.5112,
      "num_tokens": 351296309.0,
      "step": 460
    },
    {
      "epoch": 0.6343792633015006,
      "grad_norm": 0.23936094343662262,
      "learning_rate": 1.9645707231188742e-05,
      "loss": 0.5055,
      "num_tokens": 355112109.0,
      "step": 465
    },
    {
      "epoch": 0.6412005457025921,
      "grad_norm": 0.23796042799949646,
      "learning_rate": 1.9171891504851925e-05,
      "loss": 0.5243,
      "num_tokens": 358904864.0,
      "step": 470
    },
    {
      "epoch": 0.6480218281036835,
      "grad_norm": 0.2545931339263916,
      "learning_rate": 1.8702317569013094e-05,
      "loss": 0.5002,
      "num_tokens": 362651560.0,
      "step": 475
    },
    {
      "epoch": 0.654843110504775,
      "grad_norm": 0.23106758296489716,
      "learning_rate": 1.8237224593738327e-05,
      "loss": 0.5025,
      "num_tokens": 366319152.0,
      "step": 480
    },
    {
      "epoch": 0.6616643929058663,
      "grad_norm": 0.22513054311275482,
      "learning_rate": 1.7776849466787223e-05,
      "loss": 0.5168,
      "num_tokens": 370176088.0,
      "step": 485
    },
    {
      "epoch": 0.6684856753069577,
      "grad_norm": 0.23235899209976196,
      "learning_rate": 1.7321426672957896e-05,
      "loss": 0.5022,
      "num_tokens": 374011109.0,
      "step": 490
    },
    {
      "epoch": 0.6753069577080492,
      "grad_norm": 0.2550266683101654,
      "learning_rate": 1.6871188174655787e-05,
      "loss": 0.4954,
      "num_tokens": 377769452.0,
      "step": 495
    },
    {
      "epoch": 0.6821282401091405,
      "grad_norm": 0.23668882250785828,
      "learning_rate": 1.6426363293747334e-05,
      "loss": 0.4998,
      "num_tokens": 381536770.0,
      "step": 500
    },
    {
      "epoch": 0.6889495225102319,
      "grad_norm": 0.24165432155132294,
      "learning_rate": 1.598717859475846e-05,
      "loss": 0.5084,
      "num_tokens": 385264947.0,
      "step": 505
    },
    {
      "epoch": 0.6957708049113234,
      "grad_norm": 0.235661581158638,
      "learning_rate": 1.5553857769477553e-05,
      "loss": 0.5052,
      "num_tokens": 389008667.0,
      "step": 510
    },
    {
      "epoch": 0.7025920873124147,
      "grad_norm": 0.2295641452074051,
      "learning_rate": 1.5126621523021518e-05,
      "loss": 0.5097,
      "num_tokens": 392845122.0,
      "step": 515
    },
    {
      "epoch": 0.7094133697135061,
      "grad_norm": 0.259378582239151,
      "learning_rate": 1.4705687461423209e-05,
      "loss": 0.522,
      "num_tokens": 396569410.0,
      "step": 520
    },
    {
      "epoch": 0.7162346521145976,
      "grad_norm": 0.24214191734790802,
      "learning_rate": 1.4291269980797139e-05,
      "loss": 0.5062,
      "num_tokens": 400328978.0,
      "step": 525
    },
    {
      "epoch": 0.723055934515689,
      "grad_norm": 0.22774960100650787,
      "learning_rate": 1.3883580158140291e-05,
      "loss": 0.5002,
      "num_tokens": 404085025.0,
      "step": 530
    },
    {
      "epoch": 0.7298772169167803,
      "grad_norm": 0.21534228324890137,
      "learning_rate": 1.3482825643823293e-05,
      "loss": 0.5058,
      "num_tokens": 407976499.0,
      "step": 535
    },
    {
      "epoch": 0.7366984993178718,
      "grad_norm": 0.21766649186611176,
      "learning_rate": 1.3089210555827086e-05,
      "loss": 0.5116,
      "num_tokens": 411774021.0,
      "step": 540
    },
    {
      "epoch": 0.7435197817189632,
      "grad_norm": 0.21238680183887482,
      "learning_rate": 1.270293537577855e-05,
      "loss": 0.5145,
      "num_tokens": 415754417.0,
      "step": 545
    },
    {
      "epoch": 0.7503410641200545,
      "grad_norm": 0.22271254658699036,
      "learning_rate": 1.232419684683844e-05,
      "loss": 0.4992,
      "num_tokens": 419428701.0,
      "step": 550
    },
    {
      "epoch": 0.757162346521146,
      "grad_norm": 0.22422295808792114,
      "learning_rate": 1.1953187873493303e-05,
      "loss": 0.4998,
      "num_tokens": 423056747.0,
      "step": 555
    },
    {
      "epoch": 0.7639836289222374,
      "grad_norm": 0.2289811670780182,
      "learning_rate": 1.1590097423302684e-05,
      "loss": 0.4957,
      "num_tokens": 426771236.0,
      "step": 560
    },
    {
      "epoch": 0.7708049113233287,
      "grad_norm": 0.21832554042339325,
      "learning_rate": 1.1235110430651421e-05,
      "loss": 0.4956,
      "num_tokens": 430648058.0,
      "step": 565
    },
    {
      "epoch": 0.7776261937244202,
      "grad_norm": 0.23512613773345947,
      "learning_rate": 1.0888407702556284e-05,
      "loss": 0.4995,
      "num_tokens": 434432023.0,
      "step": 570
    },
    {
      "epoch": 0.7844474761255116,
      "grad_norm": 0.2369619607925415,
      "learning_rate": 1.0550165826574766e-05,
      "loss": 0.4993,
      "num_tokens": 438355231.0,
      "step": 575
    },
    {
      "epoch": 0.791268758526603,
      "grad_norm": 0.23256513476371765,
      "learning_rate": 1.0220557080862985e-05,
      "loss": 0.5145,
      "num_tokens": 442388385.0,
      "step": 580
    },
    {
      "epoch": 0.7980900409276944,
      "grad_norm": 0.2141689658164978,
      "learning_rate": 9.899749346428556e-06,
      "loss": 0.5017,
      "num_tokens": 446189045.0,
      "step": 585
    },
    {
      "epoch": 0.8049113233287858,
      "grad_norm": 0.2098773866891861,
      "learning_rate": 9.587906021623016e-06,
      "loss": 0.5158,
      "num_tokens": 450018716.0,
      "step": 590
    },
    {
      "epoch": 0.8117326057298773,
      "grad_norm": 0.23991893231868744,
      "learning_rate": 9.28518593891749e-06,
      "loss": 0.501,
      "num_tokens": 453809691.0,
      "step": 595
    },
    {
      "epoch": 0.8185538881309686,
      "grad_norm": 0.22266173362731934,
      "learning_rate": 8.99174328400385e-06,
      "loss": 0.4993,
      "num_tokens": 457645977.0,
      "step": 600
    },
    {
      "epoch": 0.82537517053206,
      "grad_norm": 0.2336045503616333,
      "learning_rate": 8.707727517262697e-06,
      "loss": 0.5047,
      "num_tokens": 461370305.0,
      "step": 605
    },
    {
      "epoch": 0.8321964529331515,
      "grad_norm": 0.20964659750461578,
      "learning_rate": 8.433283297638053e-06,
      "loss": 0.4989,
      "num_tokens": 465282670.0,
      "step": 610
    },
    {
      "epoch": 0.8390177353342428,
      "grad_norm": 0.21320775151252747,
      "learning_rate": 8.168550408957632e-06,
      "loss": 0.4967,
      "num_tokens": 469094631.0,
      "step": 615
    },
    {
      "epoch": 0.8458390177353342,
      "grad_norm": 0.22750438749790192,
      "learning_rate": 7.91366368873613e-06,
      "loss": 0.4941,
      "num_tokens": 472868071.0,
      "step": 620
    },
    {
      "epoch": 0.8526603001364257,
      "grad_norm": 0.225652813911438,
      "learning_rate": 7.66875295949791e-06,
      "loss": 0.5101,
      "num_tokens": 476693164.0,
      "step": 625
    },
    {
      "epoch": 0.859481582537517,
      "grad_norm": 0.2049553096294403,
      "learning_rate": 7.4339429626539e-06,
      "loss": 0.5098,
      "num_tokens": 480634992.0,
      "step": 630
    },
    {
      "epoch": 0.8663028649386084,
      "grad_norm": 0.2328362911939621,
      "learning_rate": 7.2093532949665715e-06,
      "loss": 0.5077,
      "num_tokens": 484452349.0,
      "step": 635
    },
    {
      "epoch": 0.8731241473396999,
      "grad_norm": 0.20552393794059753,
      "learning_rate": 6.995098347635173e-06,
      "loss": 0.493,
      "num_tokens": 488334317.0,
      "step": 640
    },
    {
      "epoch": 0.8799454297407913,
      "grad_norm": 0.20875284075737,
      "learning_rate": 6.791287248032431e-06,
      "loss": 0.4962,
      "num_tokens": 492162119.0,
      "step": 645
    },
    {
      "epoch": 0.8867667121418826,
      "grad_norm": 0.21407166123390198,
      "learning_rate": 6.598023804122194e-06,
      "loss": 0.5035,
      "num_tokens": 496169094.0,
      "step": 650
    },
    {
      "epoch": 0.8935879945429741,
      "grad_norm": 0.20252534747123718,
      "learning_rate": 6.415406451586528e-06,
      "loss": 0.499,
      "num_tokens": 500122283.0,
      "step": 655
    },
    {
      "epoch": 0.9004092769440655,
      "grad_norm": 0.20611464977264404,
      "learning_rate": 6.243528203689025e-06,
      "loss": 0.5028,
      "num_tokens": 504062446.0,
      "step": 660
    },
    {
      "epoch": 0.9072305593451568,
      "grad_norm": 0.2153824418783188,
      "learning_rate": 6.0824766039e-06,
      "loss": 0.499,
      "num_tokens": 507853633.0,
      "step": 665
    },
    {
      "epoch": 0.9140518417462483,
      "grad_norm": 0.20805135369300842,
      "learning_rate": 5.932333681307571e-06,
      "loss": 0.5058,
      "num_tokens": 511714869.0,
      "step": 670
    },
    {
      "epoch": 0.9208731241473397,
      "grad_norm": 0.2085290253162384,
      "learning_rate": 5.793175908837471e-06,
      "loss": 0.4964,
      "num_tokens": 515451192.0,
      "step": 675
    },
    {
      "epoch": 0.927694406548431,
      "grad_norm": 0.20749785006046295,
      "learning_rate": 5.665074164302742e-06,
      "loss": 0.506,
      "num_tokens": 519195745.0,
      "step": 680
    },
    {
      "epoch": 0.9345156889495225,
      "grad_norm": 0.19413329660892487,
      "learning_rate": 5.548093694303275e-06,
      "loss": 0.4915,
      "num_tokens": 523017567.0,
      "step": 685
    },
    {
      "epoch": 0.9413369713506139,
      "grad_norm": 0.21901412308216095,
      "learning_rate": 5.442294080993446e-06,
      "loss": 0.5056,
      "num_tokens": 526884969.0,
      "step": 690
    },
    {
      "epoch": 0.9481582537517054,
      "grad_norm": 0.20552243292331696,
      "learning_rate": 5.347729211734919e-06,
      "loss": 0.503,
      "num_tokens": 530678785.0,
      "step": 695
    },
    {
      "epoch": 0.9549795361527967,
      "grad_norm": 0.20113253593444824,
      "learning_rate": 5.264447251649954e-06,
      "loss": 0.5055,
      "num_tokens": 534460009.0,
      "step": 700
    },
    {
      "epoch": 0.9618008185538881,
      "grad_norm": 0.2043074369430542,
      "learning_rate": 5.192490619089267e-06,
      "loss": 0.4897,
      "num_tokens": 538338585.0,
      "step": 705
    },
    {
      "epoch": 0.9686221009549796,
      "grad_norm": 0.2070448249578476,
      "learning_rate": 5.1318959640269095e-06,
      "loss": 0.5002,
      "num_tokens": 542019550.0,
      "step": 710
    },
    {
      "epoch": 0.975443383356071,
      "grad_norm": 0.21117159724235535,
      "learning_rate": 5.082694149393189e-06,
      "loss": 0.5111,
      "num_tokens": 545767802.0,
      "step": 715
    },
    {
      "epoch": 0.9822646657571623,
      "grad_norm": 0.20505015552043915,
      "learning_rate": 5.044910235355121e-06,
      "loss": 0.497,
      "num_tokens": 549561878.0,
      "step": 720
    },
    {
      "epoch": 0.9890859481582538,
      "grad_norm": 0.19267314672470093,
      "learning_rate": 5.0185634665524255e-06,
      "loss": 0.493,
      "num_tokens": 553402412.0,
      "step": 725
    },
    {
      "epoch": 0.9959072305593452,
      "grad_norm": 0.18925239145755768,
      "learning_rate": 5.003667262295572e-06,
      "loss": 0.5012,
      "num_tokens": 557174057.0,
      "step": 730
    },
    {
      "epoch": 1.0,
      "num_tokens": 559480552.0,
      "step": 733,
      "total_flos": 1.0371853292601868e+19,
      "train_loss": 0.5346580615310357,
      "train_runtime": 5110.5186,
      "train_samples_per_second": 18.341,
      "train_steps_per_second": 0.143
    }
  ],
  "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
}