{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9983498349834984,
  "eval_steps": 500,
  "global_step": 605,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00825082508250825,
      "grad_norm": 0.1109217901630045,
      "learning_rate": 9.230977828571428e-06,
      "loss": 0.6996,
      "step": 5
    },
    {
      "epoch": 0.0165016501650165,
      "grad_norm": 0.1079280711895366,
      "learning_rate": 2.0769700114285712e-05,
      "loss": 0.7131,
      "step": 10
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 0.12194277489126788,
      "learning_rate": 3.23084224e-05,
      "loss": 0.7076,
      "step": 15
    },
    {
      "epoch": 0.033003300330033,
      "grad_norm": 0.11703283788506436,
      "learning_rate": 4.384714468571428e-05,
      "loss": 0.7309,
      "step": 20
    },
    {
      "epoch": 0.041254125412541254,
      "grad_norm": 0.13195891160346676,
      "learning_rate": 5.5385866971428566e-05,
      "loss": 0.7281,
      "step": 25
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 0.1086769468743628,
      "learning_rate": 6.692458925714286e-05,
      "loss": 0.6704,
      "step": 30
    },
    {
      "epoch": 0.057755775577557754,
      "grad_norm": 0.10133228628071816,
      "learning_rate": 7.846331154285714e-05,
      "loss": 0.66,
      "step": 35
    },
    {
      "epoch": 0.066006600660066,
      "grad_norm": 0.10991596007303452,
      "learning_rate": 8.077030373253913e-05,
      "loss": 0.6782,
      "step": 40
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 0.10299322280255592,
      "learning_rate": 8.076724771002127e-05,
      "loss": 0.6333,
      "step": 45
    },
    {
      "epoch": 0.08250825082508251,
      "grad_norm": 0.10765477907576462,
      "learning_rate": 8.076184115273458e-05,
      "loss": 0.6667,
      "step": 50
    },
    {
      "epoch": 0.09075907590759076,
      "grad_norm": 0.09592084729245812,
      "learning_rate": 8.0754084480298e-05,
      "loss": 0.6638,
      "step": 55
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 0.10331536135213028,
      "learning_rate": 8.074397829472986e-05,
      "loss": 0.7187,
      "step": 60
    },
    {
      "epoch": 0.10726072607260725,
      "grad_norm": 0.11074455533529015,
      "learning_rate": 8.073152338040115e-05,
      "loss": 0.7264,
      "step": 65
    },
    {
      "epoch": 0.11551155115511551,
      "grad_norm": 0.11331253823850916,
      "learning_rate": 8.071672070397465e-05,
      "loss": 0.6979,
      "step": 70
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 0.09909826847951773,
      "learning_rate": 8.069957141432996e-05,
      "loss": 0.6886,
      "step": 75
    },
    {
      "epoch": 0.132013201320132,
      "grad_norm": 0.1102036040341218,
      "learning_rate": 8.068007684247422e-05,
      "loss": 0.7248,
      "step": 80
    },
    {
      "epoch": 0.14026402640264027,
      "grad_norm": 0.10233573035333016,
      "learning_rate": 8.065823850143891e-05,
      "loss": 0.7007,
      "step": 85
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 0.11318472169518733,
      "learning_rate": 8.063405808616236e-05,
      "loss": 0.7065,
      "step": 90
    },
    {
      "epoch": 0.15676567656765678,
      "grad_norm": 0.09736084830545598,
      "learning_rate": 8.060753747335823e-05,
      "loss": 0.6768,
      "step": 95
    },
    {
      "epoch": 0.16501650165016502,
      "grad_norm": 0.10655098611266442,
      "learning_rate": 8.057867872136982e-05,
      "loss": 0.6811,
      "step": 100
    },
    {
      "epoch": 0.17326732673267325,
      "grad_norm": 0.10235404832102123,
      "learning_rate": 8.054748407001038e-05,
      "loss": 0.705,
      "step": 105
    },
    {
      "epoch": 0.18151815181518152,
      "grad_norm": 0.11226503528883268,
      "learning_rate": 8.051395594038919e-05,
      "loss": 0.6616,
      "step": 110
    },
    {
      "epoch": 0.18976897689768976,
      "grad_norm": 0.10423993294609094,
      "learning_rate": 8.04780969347237e-05,
      "loss": 0.7013,
      "step": 115
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 0.09696063297767098,
      "learning_rate": 8.043990983613759e-05,
      "loss": 0.7077,
      "step": 120
    },
    {
      "epoch": 0.20627062706270627,
      "grad_norm": 0.1023779789220443,
      "learning_rate": 8.039939760844466e-05,
      "loss": 0.6759,
      "step": 125
    },
    {
      "epoch": 0.2145214521452145,
      "grad_norm": 0.10241506704665838,
      "learning_rate": 8.035656339591892e-05,
      "loss": 0.701,
      "step": 130
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 0.10783128023486195,
      "learning_rate": 8.031141052305049e-05,
      "loss": 0.6905,
      "step": 135
    },
    {
      "epoch": 0.23102310231023102,
      "grad_norm": 0.10259339913296676,
      "learning_rate": 8.026394249428757e-05,
      "loss": 0.7042,
      "step": 140
    },
    {
      "epoch": 0.23927392739273928,
      "grad_norm": 0.10386332679268319,
      "learning_rate": 8.021416299376446e-05,
      "loss": 0.6847,
      "step": 145
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 0.10727312758751012,
      "learning_rate": 8.01620758850157e-05,
      "loss": 0.7158,
      "step": 150
    },
    {
      "epoch": 0.25577557755775576,
      "grad_norm": 0.10081199335904906,
      "learning_rate": 8.010768521067604e-05,
      "loss": 0.7314,
      "step": 155
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 0.09947690530809786,
      "learning_rate": 8.005099519216686e-05,
      "loss": 0.6556,
      "step": 160
    },
    {
      "epoch": 0.2722772277227723,
      "grad_norm": 0.0998920584555826,
      "learning_rate": 7.999201022936842e-05,
      "loss": 0.6959,
      "step": 165
    },
    {
      "epoch": 0.28052805280528054,
      "grad_norm": 0.10002463919928152,
      "learning_rate": 7.993073490027837e-05,
      "loss": 0.6676,
      "step": 170
    },
    {
      "epoch": 0.2887788778877888,
      "grad_norm": 0.09795956362270347,
      "learning_rate": 7.986717396065655e-05,
      "loss": 0.6991,
      "step": 175
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 0.09999716542424185,
      "learning_rate": 7.980133234365572e-05,
      "loss": 0.6867,
      "step": 180
    },
    {
      "epoch": 0.30528052805280526,
      "grad_norm": 0.110570313613684,
      "learning_rate": 7.973321515943883e-05,
      "loss": 0.7301,
      "step": 185
    },
    {
      "epoch": 0.31353135313531355,
      "grad_norm": 0.09730577084971076,
      "learning_rate": 7.966282769478233e-05,
      "loss": 0.6784,
      "step": 190
    },
    {
      "epoch": 0.3217821782178218,
      "grad_norm": 0.10249606843125265,
      "learning_rate": 7.959017541266581e-05,
      "loss": 0.7077,
      "step": 195
    },
    {
      "epoch": 0.33003300330033003,
      "grad_norm": 0.10212092732514494,
      "learning_rate": 7.951526395184813e-05,
      "loss": 0.6826,
      "step": 200
    },
    {
      "epoch": 0.33828382838283827,
      "grad_norm": 0.11727787532779357,
      "learning_rate": 7.943809912642963e-05,
      "loss": 0.656,
      "step": 205
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 0.1004631402576947,
      "learning_rate": 7.935868692540102e-05,
      "loss": 0.6927,
      "step": 210
    },
    {
      "epoch": 0.3547854785478548,
      "grad_norm": 0.10355590169694925,
      "learning_rate": 7.927703351217842e-05,
      "loss": 0.7195,
      "step": 215
    },
    {
      "epoch": 0.36303630363036304,
      "grad_norm": 0.11016608834417882,
      "learning_rate": 7.919314522412511e-05,
      "loss": 0.7359,
      "step": 220
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 0.10627797656006266,
      "learning_rate": 7.910702857205961e-05,
      "loss": 0.7205,
      "step": 225
    },
    {
      "epoch": 0.3795379537953795,
      "grad_norm": 0.10013473212295951,
      "learning_rate": 7.901869023975037e-05,
      "loss": 0.6766,
      "step": 230
    },
    {
      "epoch": 0.38778877887788776,
      "grad_norm": 0.11465309438007484,
      "learning_rate": 7.892813708339704e-05,
      "loss": 0.6874,
      "step": 235
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.10038189798772329,
      "learning_rate": 7.883537613109833e-05,
      "loss": 0.6474,
      "step": 240
    },
    {
      "epoch": 0.4042904290429043,
      "grad_norm": 0.10421646450135963,
      "learning_rate": 7.874041458230648e-05,
      "loss": 0.703,
      "step": 245
    },
    {
      "epoch": 0.41254125412541254,
      "grad_norm": 0.12217594041209018,
      "learning_rate": 7.864325980726862e-05,
      "loss": 0.703,
      "step": 250
    },
    {
      "epoch": 0.4207920792079208,
      "grad_norm": 0.11252410565227859,
      "learning_rate": 7.854391934645459e-05,
      "loss": 0.6955,
      "step": 255
    },
    {
      "epoch": 0.429042904290429,
      "grad_norm": 0.12078102363224934,
      "learning_rate": 7.844240090997184e-05,
      "loss": 0.701,
      "step": 260
    },
    {
      "epoch": 0.4372937293729373,
      "grad_norm": 0.10863585586575093,
      "learning_rate": 7.833871237696693e-05,
      "loss": 0.7132,
      "step": 265
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 0.09563437176495763,
      "learning_rate": 7.823286179501403e-05,
      "loss": 0.6858,
      "step": 270
    },
    {
      "epoch": 0.4537953795379538,
      "grad_norm": 0.11421103818288875,
      "learning_rate": 7.812485737949037e-05,
      "loss": 0.7121,
      "step": 275
    },
    {
      "epoch": 0.46204620462046203,
      "grad_norm": 0.11953247382851949,
      "learning_rate": 7.801470751293855e-05,
      "loss": 0.6956,
      "step": 280
    },
    {
      "epoch": 0.47029702970297027,
      "grad_norm": 0.1266115959025527,
      "learning_rate": 7.790242074441599e-05,
      "loss": 0.688,
      "step": 285
    },
    {
      "epoch": 0.47854785478547857,
      "grad_norm": 0.11648609420312882,
      "learning_rate": 7.778800578883142e-05,
      "loss": 0.6911,
      "step": 290
    },
    {
      "epoch": 0.4867986798679868,
      "grad_norm": 0.11762881099851867,
      "learning_rate": 7.767147152626842e-05,
      "loss": 0.6945,
      "step": 295
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 0.11429683321227115,
      "learning_rate": 7.755282700129635e-05,
      "loss": 0.6892,
      "step": 300
    },
    {
      "epoch": 0.5033003300330033,
      "grad_norm": 0.10450773160582569,
      "learning_rate": 7.743208142226819e-05,
      "loss": 0.6391,
      "step": 305
    },
    {
      "epoch": 0.5115511551155115,
      "grad_norm": 0.10219535497500513,
      "learning_rate": 7.730924416060601e-05,
      "loss": 0.724,
      "step": 310
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 0.11574609265433186,
      "learning_rate": 7.718432475007354e-05,
      "loss": 0.6826,
      "step": 315
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 0.11217826609258046,
      "learning_rate": 7.705733288603626e-05,
      "loss": 0.6785,
      "step": 320
    },
    {
      "epoch": 0.5363036303630363,
      "grad_norm": 0.11299742998586312,
      "learning_rate": 7.69282784247089e-05,
      "loss": 0.6792,
      "step": 325
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 0.10824042743323972,
      "learning_rate": 7.67971713823905e-05,
      "loss": 0.6698,
      "step": 330
    },
    {
      "epoch": 0.5528052805280528,
      "grad_norm": 0.11309367124567228,
      "learning_rate": 7.666402193468696e-05,
      "loss": 0.6736,
      "step": 335
    },
    {
      "epoch": 0.5610561056105611,
      "grad_norm": 0.12167568253923927,
      "learning_rate": 7.65288404157213e-05,
      "loss": 0.7555,
      "step": 340
    },
    {
      "epoch": 0.5693069306930693,
      "grad_norm": 0.0970452786135373,
      "learning_rate": 7.639163731733167e-05,
      "loss": 0.6637,
      "step": 345
    },
    {
      "epoch": 0.5775577557755776,
      "grad_norm": 0.10398626019080046,
      "learning_rate": 7.625242328825694e-05,
      "loss": 0.667,
      "step": 350
    },
    {
      "epoch": 0.5858085808580858,
      "grad_norm": 0.10466469521267713,
      "learning_rate": 7.611120913331026e-05,
      "loss": 0.6685,
      "step": 355
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.09699310632336781,
      "learning_rate": 7.59680058125405e-05,
      "loss": 0.6544,
      "step": 360
    },
    {
      "epoch": 0.6023102310231023,
      "grad_norm": 0.1045628282615931,
      "learning_rate": 7.582282444038156e-05,
      "loss": 0.6857,
      "step": 365
    },
    {
      "epoch": 0.6105610561056105,
      "grad_norm": 0.11520677189307071,
      "learning_rate": 7.567567628478979e-05,
      "loss": 0.7186,
      "step": 370
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 0.11447834758784298,
      "learning_rate": 7.552657276636944e-05,
      "loss": 0.7113,
      "step": 375
    },
    {
      "epoch": 0.6270627062706271,
      "grad_norm": 0.1016515991153301,
      "learning_rate": 7.53755254574862e-05,
      "loss": 0.6624,
      "step": 380
    },
    {
      "epoch": 0.6353135313531353,
      "grad_norm": 0.10741656629850158,
      "learning_rate": 7.522254608136916e-05,
      "loss": 0.6907,
      "step": 385
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 0.108251704550908,
      "learning_rate": 7.506764651120083e-05,
      "loss": 0.7164,
      "step": 390
    },
    {
      "epoch": 0.6518151815181518,
      "grad_norm": 0.11089125041915984,
      "learning_rate": 7.49108387691957e-05,
      "loss": 0.6801,
      "step": 395
    },
    {
      "epoch": 0.6600660066006601,
      "grad_norm": 0.10269781298675916,
      "learning_rate": 7.475213502566708e-05,
      "loss": 0.6819,
      "step": 400
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 0.11063903685541557,
      "learning_rate": 7.459154759808266e-05,
      "loss": 0.668,
      "step": 405
    },
    {
      "epoch": 0.6765676567656765,
      "grad_norm": 0.11520213411474844,
      "learning_rate": 7.442908895010832e-05,
      "loss": 0.706,
      "step": 410
    },
    {
      "epoch": 0.6848184818481848,
      "grad_norm": 0.11340826064845087,
      "learning_rate": 7.4264771690641e-05,
      "loss": 0.7203,
      "step": 415
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 0.10182339826739246,
      "learning_rate": 7.40986085728299e-05,
      "loss": 0.6611,
      "step": 420
    },
    {
      "epoch": 0.7013201320132013,
      "grad_norm": 0.11114269495165541,
      "learning_rate": 7.393061249308681e-05,
      "loss": 0.6717,
      "step": 425
    },
    {
      "epoch": 0.7095709570957096,
      "grad_norm": 0.11971729469914588,
      "learning_rate": 7.37607964900851e-05,
      "loss": 0.6721,
      "step": 430
    },
    {
      "epoch": 0.7178217821782178,
      "grad_norm": 0.11365942077245782,
      "learning_rate": 7.358917374374776e-05,
      "loss": 0.7085,
      "step": 435
    },
    {
      "epoch": 0.7260726072607261,
      "grad_norm": 0.11543073343399962,
      "learning_rate": 7.341575757422454e-05,
      "loss": 0.7003,
      "step": 440
    },
    {
      "epoch": 0.7343234323432343,
      "grad_norm": 0.10987487064626321,
      "learning_rate": 7.324056144085803e-05,
      "loss": 0.6966,
      "step": 445
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.11020238714339606,
      "learning_rate": 7.306359894113908e-05,
      "loss": 0.7114,
      "step": 450
    },
    {
      "epoch": 0.7508250825082509,
      "grad_norm": 0.11209340274285112,
      "learning_rate": 7.288488380965147e-05,
      "loss": 0.7218,
      "step": 455
    },
    {
      "epoch": 0.759075907590759,
      "grad_norm": 0.12877531625779254,
      "learning_rate": 7.270442991700595e-05,
      "loss": 0.6982,
      "step": 460
    },
    {
      "epoch": 0.7673267326732673,
      "grad_norm": 0.1117598157414889,
      "learning_rate": 7.252225126876367e-05,
      "loss": 0.7212,
      "step": 465
    },
    {
      "epoch": 0.7755775577557755,
      "grad_norm": 0.11279697876757706,
      "learning_rate": 7.233836200434913e-05,
      "loss": 0.6573,
      "step": 470
    },
    {
      "epoch": 0.7838283828382838,
      "grad_norm": 0.11434280774159107,
      "learning_rate": 7.215277639595287e-05,
      "loss": 0.6949,
      "step": 475
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.11543489128107651,
      "learning_rate": 7.196550884742365e-05,
      "loss": 0.674,
      "step": 480
    },
    {
      "epoch": 0.8003300330033003,
      "grad_norm": 0.11611954417882157,
      "learning_rate": 7.177657389315065e-05,
      "loss": 0.6863,
      "step": 485
    },
    {
      "epoch": 0.8085808580858086,
      "grad_norm": 0.119116453091791,
      "learning_rate": 7.158598619693533e-05,
      "loss": 0.6645,
      "step": 490
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 0.12456425654504054,
      "learning_rate": 7.13937605508533e-05,
      "loss": 0.7223,
      "step": 495
    },
    {
      "epoch": 0.8250825082508251,
      "grad_norm": 0.11284151814874993,
      "learning_rate": 7.11999118741064e-05,
      "loss": 0.6958,
      "step": 500
    },
    {
      "epoch": 0.8250825082508251,
      "eval_loss": 0.815915584564209,
      "eval_runtime": 41.4268,
      "eval_samples_per_second": 1.521,
      "eval_steps_per_second": 0.193,
      "step": 500
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.1230250072514643,
      "learning_rate": 7.10044552118646e-05,
      "loss": 0.6802,
      "step": 505
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 0.12299958189793461,
      "learning_rate": 7.080740573409843e-05,
      "loss": 0.7014,
      "step": 510
    },
    {
      "epoch": 0.8498349834983498,
      "grad_norm": 0.11213431363226725,
      "learning_rate": 7.060877873440157e-05,
      "loss": 0.7014,
      "step": 515
    },
    {
      "epoch": 0.858085808580858,
      "grad_norm": 0.123893410660033,
      "learning_rate": 7.04085896288038e-05,
      "loss": 0.6833,
      "step": 520
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 0.10624694364468523,
      "learning_rate": 7.02068539545746e-05,
      "loss": 0.6485,
      "step": 525
    },
    {
      "epoch": 0.8745874587458746,
      "grad_norm": 0.11161342962422176,
      "learning_rate": 7.000358736901722e-05,
      "loss": 0.6752,
      "step": 530
    },
    {
      "epoch": 0.8828382838283828,
      "grad_norm": 0.11213055579397066,
      "learning_rate": 6.979880564825346e-05,
      "loss": 0.6999,
      "step": 535
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 0.11735024742206589,
      "learning_rate": 6.959252468599926e-05,
      "loss": 0.6589,
      "step": 540
    },
    {
      "epoch": 0.8993399339933993,
      "grad_norm": 0.11402736912729902,
      "learning_rate": 6.938476049233114e-05,
      "loss": 0.695,
      "step": 545
    },
    {
      "epoch": 0.9075907590759076,
      "grad_norm": 0.11257498599338571,
      "learning_rate": 6.917552919244357e-05,
      "loss": 0.6814,
      "step": 550
    },
    {
      "epoch": 0.9158415841584159,
      "grad_norm": 0.12373640269866129,
      "learning_rate": 6.896484702539755e-05,
      "loss": 0.684,
      "step": 555
    },
    {
      "epoch": 0.9240924092409241,
      "grad_norm": 0.11956271635788736,
      "learning_rate": 6.875273034286008e-05,
      "loss": 0.69,
      "step": 560
    },
    {
      "epoch": 0.9323432343234324,
      "grad_norm": 0.10785285284383107,
      "learning_rate": 6.853919560783526e-05,
      "loss": 0.7083,
      "step": 565
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 0.10722760959275023,
      "learning_rate": 6.832425939338633e-05,
      "loss": 0.6677,
      "step": 570
    },
    {
      "epoch": 0.9488448844884488,
      "grad_norm": 0.10277491090545628,
      "learning_rate": 6.810793838134964e-05,
      "loss": 0.6698,
      "step": 575
    },
    {
      "epoch": 0.9570957095709571,
      "grad_norm": 0.1063963058179587,
      "learning_rate": 6.789024936103965e-05,
      "loss": 0.6663,
      "step": 580
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 0.1147344164814247,
      "learning_rate": 6.767120922794605e-05,
      "loss": 0.7234,
      "step": 585
    },
    {
      "epoch": 0.9735973597359736,
      "grad_norm": 0.1060126783103328,
      "learning_rate": 6.745083498242244e-05,
      "loss": 0.7153,
      "step": 590
    },
    {
      "epoch": 0.9818481848184818,
      "grad_norm": 0.11660595329599203,
      "learning_rate": 6.722914372836674e-05,
      "loss": 0.7178,
      "step": 595
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 0.11158768870366531,
      "learning_rate": 6.700615267189389e-05,
      "loss": 0.6616,
      "step": 600
    },
    {
      "epoch": 0.9983498349834984,
      "grad_norm": 0.12537561554397872,
      "learning_rate": 6.67818791200003e-05,
      "loss": 0.6907,
      "step": 605
    },
    {
      "epoch": 0.9983498349834984,
      "eval_loss": 0.8133310079574585,
      "eval_runtime": 39.2156,
      "eval_samples_per_second": 1.607,
      "eval_steps_per_second": 0.204,
      "step": 605
    }
  ],
  "logging_steps": 5,
  "max_steps": 1818,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 627526934200320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}