{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1281,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0234192037470726,
      "grad_norm": 2.481647447902812,
      "learning_rate": 5e-06,
      "loss": 0.7124,
      "step": 10
    },
    {
      "epoch": 0.0468384074941452,
      "grad_norm": 0.7262736099420435,
      "learning_rate": 5e-06,
      "loss": 0.6153,
      "step": 20
    },
    {
      "epoch": 0.0702576112412178,
      "grad_norm": 0.7790978795240339,
      "learning_rate": 5e-06,
      "loss": 0.5859,
      "step": 30
    },
    {
      "epoch": 0.0936768149882904,
      "grad_norm": 0.6467962423003429,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 40
    },
    {
      "epoch": 0.117096018735363,
      "grad_norm": 0.5143977117058031,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 50
    },
    {
      "epoch": 0.1405152224824356,
      "grad_norm": 0.600469324649081,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 60
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.5054683279603859,
      "learning_rate": 5e-06,
      "loss": 0.555,
      "step": 70
    },
    {
      "epoch": 0.1873536299765808,
      "grad_norm": 0.520518786315232,
      "learning_rate": 5e-06,
      "loss": 0.548,
      "step": 80
    },
    {
      "epoch": 0.2107728337236534,
      "grad_norm": 1.008487324396366,
      "learning_rate": 5e-06,
      "loss": 0.5481,
      "step": 90
    },
    {
      "epoch": 0.234192037470726,
      "grad_norm": 0.6357300755902857,
      "learning_rate": 5e-06,
      "loss": 0.5449,
      "step": 100
    },
    {
      "epoch": 0.2576112412177986,
      "grad_norm": 0.4471586394958172,
      "learning_rate": 5e-06,
      "loss": 0.541,
      "step": 110
    },
    {
      "epoch": 0.2810304449648712,
      "grad_norm": 0.42874334693852684,
      "learning_rate": 5e-06,
      "loss": 0.5397,
      "step": 120
    },
    {
      "epoch": 0.3044496487119438,
      "grad_norm": 0.5493546613118618,
      "learning_rate": 5e-06,
      "loss": 0.5357,
      "step": 130
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.7309908680131434,
      "learning_rate": 5e-06,
      "loss": 0.535,
      "step": 140
    },
    {
      "epoch": 0.351288056206089,
      "grad_norm": 0.5231239547569523,
      "learning_rate": 5e-06,
      "loss": 0.5373,
      "step": 150
    },
    {
      "epoch": 0.3747072599531616,
      "grad_norm": 0.47995952741525777,
      "learning_rate": 5e-06,
      "loss": 0.5346,
      "step": 160
    },
    {
      "epoch": 0.3981264637002342,
      "grad_norm": 0.562861554643795,
      "learning_rate": 5e-06,
      "loss": 0.5312,
      "step": 170
    },
    {
      "epoch": 0.4215456674473068,
      "grad_norm": 0.6323157343840412,
      "learning_rate": 5e-06,
      "loss": 0.5332,
      "step": 180
    },
    {
      "epoch": 0.4449648711943794,
      "grad_norm": 0.6022835533604722,
      "learning_rate": 5e-06,
      "loss": 0.5368,
      "step": 190
    },
    {
      "epoch": 0.468384074941452,
      "grad_norm": 0.5241376216453505,
      "learning_rate": 5e-06,
      "loss": 0.5348,
      "step": 200
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.4560855929707371,
      "learning_rate": 5e-06,
      "loss": 0.5298,
      "step": 210
    },
    {
      "epoch": 0.5152224824355972,
      "grad_norm": 0.4775160386802804,
      "learning_rate": 5e-06,
      "loss": 0.527,
      "step": 220
    },
    {
      "epoch": 0.5386416861826698,
      "grad_norm": 0.5062169069603658,
      "learning_rate": 5e-06,
      "loss": 0.5295,
      "step": 230
    },
    {
      "epoch": 0.5620608899297423,
      "grad_norm": 0.43311731742710935,
      "learning_rate": 5e-06,
      "loss": 0.5264,
      "step": 240
    },
    {
      "epoch": 0.585480093676815,
      "grad_norm": 0.4911544553586758,
      "learning_rate": 5e-06,
      "loss": 0.5292,
      "step": 250
    },
    {
      "epoch": 0.6088992974238876,
      "grad_norm": 0.5749030738074241,
      "learning_rate": 5e-06,
      "loss": 0.5253,
      "step": 260
    },
    {
      "epoch": 0.6323185011709602,
      "grad_norm": 0.5580576917700846,
      "learning_rate": 5e-06,
      "loss": 0.5238,
      "step": 270
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.4760038513178861,
      "learning_rate": 5e-06,
      "loss": 0.522,
      "step": 280
    },
    {
      "epoch": 0.6791569086651054,
      "grad_norm": 0.5216361788356643,
      "learning_rate": 5e-06,
      "loss": 0.5243,
      "step": 290
    },
    {
      "epoch": 0.702576112412178,
      "grad_norm": 0.46276681576162904,
      "learning_rate": 5e-06,
      "loss": 0.5217,
      "step": 300
    },
    {
      "epoch": 0.7259953161592506,
      "grad_norm": 0.4747845254798478,
      "learning_rate": 5e-06,
      "loss": 0.5226,
      "step": 310
    },
    {
      "epoch": 0.7494145199063232,
      "grad_norm": 0.5960080896982851,
      "learning_rate": 5e-06,
      "loss": 0.521,
      "step": 320
    },
    {
      "epoch": 0.7728337236533958,
      "grad_norm": 0.5212901742846952,
      "learning_rate": 5e-06,
      "loss": 0.5201,
      "step": 330
    },
    {
      "epoch": 0.7962529274004684,
      "grad_norm": 0.5133380400247927,
      "learning_rate": 5e-06,
      "loss": 0.5199,
      "step": 340
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 0.4368489322167074,
      "learning_rate": 5e-06,
      "loss": 0.5204,
      "step": 350
    },
    {
      "epoch": 0.8430913348946136,
      "grad_norm": 0.5101656467162784,
      "learning_rate": 5e-06,
      "loss": 0.5221,
      "step": 360
    },
    {
      "epoch": 0.8665105386416861,
      "grad_norm": 0.5226647593757339,
      "learning_rate": 5e-06,
      "loss": 0.519,
      "step": 370
    },
    {
      "epoch": 0.8899297423887588,
      "grad_norm": 0.4265472443674912,
      "learning_rate": 5e-06,
      "loss": 0.5193,
      "step": 380
    },
    {
      "epoch": 0.9133489461358314,
      "grad_norm": 0.42184387318773725,
      "learning_rate": 5e-06,
      "loss": 0.5178,
      "step": 390
    },
    {
      "epoch": 0.936768149882904,
      "grad_norm": 0.4773759814767807,
      "learning_rate": 5e-06,
      "loss": 0.5201,
      "step": 400
    },
    {
      "epoch": 0.9601873536299765,
      "grad_norm": 0.5049194555570107,
      "learning_rate": 5e-06,
      "loss": 0.5146,
      "step": 410
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.4836846129062704,
      "learning_rate": 5e-06,
      "loss": 0.514,
      "step": 420
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5167434215545654,
      "eval_runtime": 41.6336,
      "eval_samples_per_second": 276.291,
      "eval_steps_per_second": 1.081,
      "step": 427
    },
    {
      "epoch": 1.0070257611241218,
      "grad_norm": 0.4520838332937754,
      "learning_rate": 5e-06,
      "loss": 0.51,
      "step": 430
    },
    {
      "epoch": 1.0304449648711944,
      "grad_norm": 0.4866921792731558,
      "learning_rate": 5e-06,
      "loss": 0.4977,
      "step": 440
    },
    {
      "epoch": 1.053864168618267,
      "grad_norm": 0.46612714801971344,
      "learning_rate": 5e-06,
      "loss": 0.4974,
      "step": 450
    },
    {
      "epoch": 1.0772833723653397,
      "grad_norm": 0.47487180548015817,
      "learning_rate": 5e-06,
      "loss": 0.4947,
      "step": 460
    },
    {
      "epoch": 1.100702576112412,
      "grad_norm": 0.5023694335040125,
      "learning_rate": 5e-06,
      "loss": 0.4909,
      "step": 470
    },
    {
      "epoch": 1.1241217798594847,
      "grad_norm": 0.5257140618717152,
      "learning_rate": 5e-06,
      "loss": 0.4932,
      "step": 480
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 0.39736116687044365,
      "learning_rate": 5e-06,
      "loss": 0.4894,
      "step": 490
    },
    {
      "epoch": 1.17096018735363,
      "grad_norm": 0.42753669693798274,
      "learning_rate": 5e-06,
      "loss": 0.4943,
      "step": 500
    },
    {
      "epoch": 1.1943793911007026,
      "grad_norm": 0.4539073963232022,
      "learning_rate": 5e-06,
      "loss": 0.497,
      "step": 510
    },
    {
      "epoch": 1.2177985948477752,
      "grad_norm": 0.40221054966287245,
      "learning_rate": 5e-06,
      "loss": 0.4916,
      "step": 520
    },
    {
      "epoch": 1.2412177985948478,
      "grad_norm": 0.40071702689512967,
      "learning_rate": 5e-06,
      "loss": 0.4904,
      "step": 530
    },
    {
      "epoch": 1.2646370023419204,
      "grad_norm": 0.4914284242936407,
      "learning_rate": 5e-06,
      "loss": 0.4941,
      "step": 540
    },
    {
      "epoch": 1.288056206088993,
      "grad_norm": 0.4409757840452587,
      "learning_rate": 5e-06,
      "loss": 0.4924,
      "step": 550
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.4137810147419586,
      "learning_rate": 5e-06,
      "loss": 0.4925,
      "step": 560
    },
    {
      "epoch": 1.334894613583138,
      "grad_norm": 0.48726970931068914,
      "learning_rate": 5e-06,
      "loss": 0.4943,
      "step": 570
    },
    {
      "epoch": 1.3583138173302107,
      "grad_norm": 0.5494057601615131,
      "learning_rate": 5e-06,
      "loss": 0.4935,
      "step": 580
    },
    {
      "epoch": 1.3817330210772834,
      "grad_norm": 0.41251177208283474,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 590
    },
    {
      "epoch": 1.405152224824356,
      "grad_norm": 0.39118790995394576,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 600
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.49321602369191925,
      "learning_rate": 5e-06,
      "loss": 0.496,
      "step": 610
    },
    {
      "epoch": 1.4519906323185012,
      "grad_norm": 0.5208838513759695,
      "learning_rate": 5e-06,
      "loss": 0.4953,
      "step": 620
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.43794255642976027,
      "learning_rate": 5e-06,
      "loss": 0.4951,
      "step": 630
    },
    {
      "epoch": 1.4988290398126463,
      "grad_norm": 0.5557497245301519,
      "learning_rate": 5e-06,
      "loss": 0.4929,
      "step": 640
    },
    {
      "epoch": 1.5222482435597189,
      "grad_norm": 0.5087889678152296,
      "learning_rate": 5e-06,
      "loss": 0.4896,
      "step": 650
    },
    {
      "epoch": 1.5456674473067915,
      "grad_norm": 0.38311143724497726,
      "learning_rate": 5e-06,
      "loss": 0.4928,
      "step": 660
    },
    {
      "epoch": 1.5690866510538641,
      "grad_norm": 0.48635422306380777,
      "learning_rate": 5e-06,
      "loss": 0.488,
      "step": 670
    },
    {
      "epoch": 1.5925058548009368,
      "grad_norm": 0.6136317892186699,
      "learning_rate": 5e-06,
      "loss": 0.4949,
      "step": 680
    },
    {
      "epoch": 1.6159250585480094,
      "grad_norm": 0.47270773640049263,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 690
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.5783159568227515,
      "learning_rate": 5e-06,
      "loss": 0.4936,
      "step": 700
    },
    {
      "epoch": 1.6627634660421546,
      "grad_norm": 0.43336426848256004,
      "learning_rate": 5e-06,
      "loss": 0.4938,
      "step": 710
    },
    {
      "epoch": 1.6861826697892273,
      "grad_norm": 0.4314026408601509,
      "learning_rate": 5e-06,
      "loss": 0.4967,
      "step": 720
    },
    {
      "epoch": 1.7096018735362999,
      "grad_norm": 0.38409075682155797,
      "learning_rate": 5e-06,
      "loss": 0.4891,
      "step": 730
    },
    {
      "epoch": 1.7330210772833725,
      "grad_norm": 0.5211936246593988,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 740
    },
    {
      "epoch": 1.756440281030445,
      "grad_norm": 0.46808950576809366,
      "learning_rate": 5e-06,
      "loss": 0.4949,
      "step": 750
    },
    {
      "epoch": 1.7798594847775175,
      "grad_norm": 0.3970884421781967,
      "learning_rate": 5e-06,
      "loss": 0.4864,
      "step": 760
    },
    {
      "epoch": 1.8032786885245902,
      "grad_norm": 0.4338133573209166,
      "learning_rate": 5e-06,
      "loss": 0.4877,
      "step": 770
    },
    {
      "epoch": 1.8266978922716628,
      "grad_norm": 0.5302929743875919,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 780
    },
    {
      "epoch": 1.8501170960187352,
      "grad_norm": 0.48309786628518675,
      "learning_rate": 5e-06,
      "loss": 0.4919,
      "step": 790
    },
    {
      "epoch": 1.8735362997658078,
      "grad_norm": 0.44165745399512696,
      "learning_rate": 5e-06,
      "loss": 0.4875,
      "step": 800
    },
    {
      "epoch": 1.8969555035128804,
      "grad_norm": 0.46223180789120477,
      "learning_rate": 5e-06,
      "loss": 0.4936,
      "step": 810
    },
    {
      "epoch": 1.920374707259953,
      "grad_norm": 0.48226738955985293,
      "learning_rate": 5e-06,
      "loss": 0.4888,
      "step": 820
    },
    {
      "epoch": 1.9437939110070257,
      "grad_norm": 0.39089405316919673,
      "learning_rate": 5e-06,
      "loss": 0.4893,
      "step": 830
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.3967255297864678,
      "learning_rate": 5e-06,
      "loss": 0.4915,
      "step": 840
    },
    {
      "epoch": 1.990632318501171,
      "grad_norm": 0.4053292002238054,
      "learning_rate": 5e-06,
      "loss": 0.4902,
      "step": 850
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5077147483825684,
      "eval_runtime": 41.7501,
      "eval_samples_per_second": 275.521,
      "eval_steps_per_second": 1.078,
      "step": 854
    },
    {
      "epoch": 2.0140515222482436,
      "grad_norm": 0.5268697371178085,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 860
    },
    {
      "epoch": 2.037470725995316,
      "grad_norm": 0.5447609017298904,
      "learning_rate": 5e-06,
      "loss": 0.4669,
      "step": 870
    },
    {
      "epoch": 2.060889929742389,
      "grad_norm": 0.5637527273857,
      "learning_rate": 5e-06,
      "loss": 0.4614,
      "step": 880
    },
    {
      "epoch": 2.0843091334894615,
      "grad_norm": 0.3841529769069848,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 890
    },
    {
      "epoch": 2.107728337236534,
      "grad_norm": 0.42444670935905104,
      "learning_rate": 5e-06,
      "loss": 0.4593,
      "step": 900
    },
    {
      "epoch": 2.1311475409836067,
      "grad_norm": 0.4111116772372611,
      "learning_rate": 5e-06,
      "loss": 0.4677,
      "step": 910
    },
    {
      "epoch": 2.1545667447306793,
      "grad_norm": 0.6373094219643812,
      "learning_rate": 5e-06,
      "loss": 0.4652,
      "step": 920
    },
    {
      "epoch": 2.177985948477752,
      "grad_norm": 0.6160202621538906,
      "learning_rate": 5e-06,
      "loss": 0.4681,
      "step": 930
    },
    {
      "epoch": 2.201405152224824,
      "grad_norm": 0.37701921381345616,
      "learning_rate": 5e-06,
      "loss": 0.4586,
      "step": 940
    },
    {
      "epoch": 2.2248243559718968,
      "grad_norm": 0.4220733688149805,
      "learning_rate": 5e-06,
      "loss": 0.4669,
      "step": 950
    },
    {
      "epoch": 2.2482435597189694,
      "grad_norm": 0.5051333977952606,
      "learning_rate": 5e-06,
      "loss": 0.4665,
      "step": 960
    },
    {
      "epoch": 2.271662763466042,
      "grad_norm": 0.45928248167044633,
      "learning_rate": 5e-06,
      "loss": 0.4665,
      "step": 970
    },
    {
      "epoch": 2.2950819672131146,
      "grad_norm": 0.4495617426425146,
      "learning_rate": 5e-06,
      "loss": 0.4662,
      "step": 980
    },
    {
      "epoch": 2.3185011709601873,
      "grad_norm": 0.4517571833465374,
      "learning_rate": 5e-06,
      "loss": 0.4646,
      "step": 990
    },
    {
      "epoch": 2.34192037470726,
      "grad_norm": 0.4138564151461986,
      "learning_rate": 5e-06,
      "loss": 0.4647,
      "step": 1000
    },
    {
      "epoch": 2.3653395784543325,
      "grad_norm": 0.5738034318601656,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 1010
    },
    {
      "epoch": 2.388758782201405,
      "grad_norm": 0.631953187344588,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 1020
    },
    {
      "epoch": 2.4121779859484778,
      "grad_norm": 0.46549566538492926,
      "learning_rate": 5e-06,
      "loss": 0.4676,
      "step": 1030
    },
    {
      "epoch": 2.4355971896955504,
      "grad_norm": 0.43668516137249047,
      "learning_rate": 5e-06,
      "loss": 0.4673,
      "step": 1040
    },
    {
      "epoch": 2.459016393442623,
      "grad_norm": 0.42948375636759983,
      "learning_rate": 5e-06,
      "loss": 0.4654,
      "step": 1050
    },
    {
      "epoch": 2.4824355971896956,
      "grad_norm": 0.4391102312189122,
      "learning_rate": 5e-06,
      "loss": 0.469,
      "step": 1060
    },
    {
      "epoch": 2.5058548009367683,
      "grad_norm": 0.49842008382902114,
      "learning_rate": 5e-06,
      "loss": 0.47,
      "step": 1070
    },
    {
      "epoch": 2.529274004683841,
      "grad_norm": 0.5588818151397613,
      "learning_rate": 5e-06,
      "loss": 0.4685,
      "step": 1080
    },
    {
      "epoch": 2.552693208430913,
      "grad_norm": 0.4037726802957124,
      "learning_rate": 5e-06,
      "loss": 0.4677,
      "step": 1090
    },
    {
      "epoch": 2.576112412177986,
      "grad_norm": 0.48821405764171133,
      "learning_rate": 5e-06,
      "loss": 0.4695,
      "step": 1100
    },
    {
      "epoch": 2.5995316159250583,
      "grad_norm": 0.3858402261553971,
      "learning_rate": 5e-06,
      "loss": 0.4677,
      "step": 1110
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.4203466943287186,
      "learning_rate": 5e-06,
      "loss": 0.4696,
      "step": 1120
    },
    {
      "epoch": 2.6463700234192036,
      "grad_norm": 0.48915413911853883,
      "learning_rate": 5e-06,
      "loss": 0.4664,
      "step": 1130
    },
    {
      "epoch": 2.669789227166276,
      "grad_norm": 0.43449855854006547,
      "learning_rate": 5e-06,
      "loss": 0.4693,
      "step": 1140
    },
    {
      "epoch": 2.693208430913349,
      "grad_norm": 0.5093894446854779,
      "learning_rate": 5e-06,
      "loss": 0.4692,
      "step": 1150
    },
    {
      "epoch": 2.7166276346604215,
      "grad_norm": 0.44982206423576104,
      "learning_rate": 5e-06,
      "loss": 0.4704,
      "step": 1160
    },
    {
      "epoch": 2.740046838407494,
      "grad_norm": 0.40753147448920485,
      "learning_rate": 5e-06,
      "loss": 0.4648,
      "step": 1170
    },
    {
      "epoch": 2.7634660421545667,
      "grad_norm": 0.36811758162537594,
      "learning_rate": 5e-06,
      "loss": 0.4629,
      "step": 1180
    },
    {
      "epoch": 2.7868852459016393,
      "grad_norm": 0.3949349460619723,
      "learning_rate": 5e-06,
      "loss": 0.4704,
      "step": 1190
    },
    {
      "epoch": 2.810304449648712,
      "grad_norm": 0.41402013254949793,
      "learning_rate": 5e-06,
      "loss": 0.4707,
      "step": 1200
    },
    {
      "epoch": 2.8337236533957846,
      "grad_norm": 0.5432806369874894,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 1210
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.3788514557857583,
      "learning_rate": 5e-06,
      "loss": 0.4711,
      "step": 1220
    },
    {
      "epoch": 2.88056206088993,
      "grad_norm": 0.39636258806401947,
      "learning_rate": 5e-06,
      "loss": 0.4653,
      "step": 1230
    },
    {
      "epoch": 2.9039812646370025,
      "grad_norm": 0.3936100271064975,
      "learning_rate": 5e-06,
      "loss": 0.4667,
      "step": 1240
    },
    {
      "epoch": 2.927400468384075,
      "grad_norm": 0.4271813759224886,
      "learning_rate": 5e-06,
      "loss": 0.4664,
      "step": 1250
    },
    {
      "epoch": 2.9508196721311473,
      "grad_norm": 0.4720023108766376,
      "learning_rate": 5e-06,
      "loss": 0.468,
      "step": 1260
    },
    {
      "epoch": 2.9742388758782203,
      "grad_norm": 0.42625818049428776,
      "learning_rate": 5e-06,
      "loss": 0.4654,
      "step": 1270
    },
    {
      "epoch": 2.9976580796252925,
      "grad_norm": 0.4282654656901964,
      "learning_rate": 5e-06,
      "loss": 0.47,
      "step": 1280
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5069288611412048,
      "eval_runtime": 41.6671,
      "eval_samples_per_second": 276.069,
      "eval_steps_per_second": 1.08,
      "step": 1281
    },
    {
      "epoch": 3.0,
      "step": 1281,
      "total_flos": 2145722711408640.0,
      "train_loss": 0.4994005665799587,
      "train_runtime": 8118.1452,
      "train_samples_per_second": 80.761,
      "train_steps_per_second": 0.158
    }
  ],
  "logging_steps": 10,
  "max_steps": 1281,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2145722711408640.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}