{
  "best_metric": 1.2894105911254883,
  "best_model_checkpoint": "miner_id_24/checkpoint-80",
  "epoch": 0.03106247793858101,
  "eval_steps": 10,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002823861630780092,
      "grad_norm": 0.6790897250175476,
      "learning_rate": 2e-05,
      "loss": 1.6543,
      "step": 1
    },
    {
      "epoch": 0.0002823861630780092,
      "eval_loss": 2.1089015007019043,
      "eval_runtime": 417.1011,
      "eval_samples_per_second": 1.789,
      "eval_steps_per_second": 1.789,
      "step": 1
    },
    {
      "epoch": 0.0005647723261560184,
      "grad_norm": 1.1645948886871338,
      "learning_rate": 4e-05,
      "loss": 2.2171,
      "step": 2
    },
    {
      "epoch": 0.0008471584892340275,
      "grad_norm": 0.4623192846775055,
      "learning_rate": 6e-05,
      "loss": 0.9606,
      "step": 3
    },
    {
      "epoch": 0.0011295446523120368,
      "grad_norm": 0.9102379679679871,
      "learning_rate": 8e-05,
      "loss": 2.5406,
      "step": 4
    },
    {
      "epoch": 0.0014119308153900459,
      "grad_norm": 1.1047648191452026,
      "learning_rate": 0.0001,
      "loss": 2.2713,
      "step": 5
    },
    {
      "epoch": 0.001694316978468055,
      "grad_norm": 0.4400641918182373,
      "learning_rate": 0.00012,
      "loss": 2.4362,
      "step": 6
    },
    {
      "epoch": 0.001976703141546064,
      "grad_norm": 0.7926576137542725,
      "learning_rate": 0.00014,
      "loss": 1.75,
      "step": 7
    },
    {
      "epoch": 0.0022590893046240735,
      "grad_norm": 0.6660397052764893,
      "learning_rate": 0.00016,
      "loss": 2.1309,
      "step": 8
    },
    {
      "epoch": 0.0025414754677020824,
      "grad_norm": 0.6158621311187744,
      "learning_rate": 0.00018,
      "loss": 2.4602,
      "step": 9
    },
    {
      "epoch": 0.0028238616307800918,
      "grad_norm": 0.9061938524246216,
      "learning_rate": 0.0002,
      "loss": 1.9124,
      "step": 10
    },
    {
      "epoch": 0.0028238616307800918,
      "eval_loss": 1.7352350950241089,
      "eval_runtime": 416.8713,
      "eval_samples_per_second": 1.79,
      "eval_steps_per_second": 1.79,
      "step": 10
    },
    {
      "epoch": 0.003106247793858101,
      "grad_norm": 0.9380114674568176,
      "learning_rate": 0.0001999979446958366,
      "loss": 1.5976,
      "step": 11
    },
    {
      "epoch": 0.00338863395693611,
      "grad_norm": 1.0424156188964844,
      "learning_rate": 0.00019999177886783194,
      "loss": 1.9498,
      "step": 12
    },
    {
      "epoch": 0.0036710201200141194,
      "grad_norm": 0.7817176580429077,
      "learning_rate": 0.00019998150276943902,
      "loss": 1.407,
      "step": 13
    },
    {
      "epoch": 0.003953406283092128,
      "grad_norm": 1.3307476043701172,
      "learning_rate": 0.000199967116823068,
      "loss": 1.9723,
      "step": 14
    },
    {
      "epoch": 0.004235792446170138,
      "grad_norm": 0.9394961595535278,
      "learning_rate": 0.0001999486216200688,
      "loss": 1.1677,
      "step": 15
    },
    {
      "epoch": 0.004518178609248147,
      "grad_norm": 3.413137435913086,
      "learning_rate": 0.00019992601792070679,
      "loss": 1.0187,
      "step": 16
    },
    {
      "epoch": 0.004800564772326156,
      "grad_norm": 3.870213747024536,
      "learning_rate": 0.00019989930665413147,
      "loss": 1.4127,
      "step": 17
    },
    {
      "epoch": 0.005082950935404165,
      "grad_norm": 0.6383346915245056,
      "learning_rate": 0.00019986848891833845,
      "loss": 1.338,
      "step": 18
    },
    {
      "epoch": 0.005365337098482174,
      "grad_norm": 1.3503261804580688,
      "learning_rate": 0.0001998335659801241,
      "loss": 0.4498,
      "step": 19
    },
    {
      "epoch": 0.0056477232615601836,
      "grad_norm": 1.6426069736480713,
      "learning_rate": 0.00019979453927503364,
      "loss": 1.7376,
      "step": 20
    },
    {
      "epoch": 0.0056477232615601836,
      "eval_loss": 1.337227702140808,
      "eval_runtime": 418.4568,
      "eval_samples_per_second": 1.783,
      "eval_steps_per_second": 1.783,
      "step": 20
    },
    {
      "epoch": 0.005930109424638193,
      "grad_norm": 1.5207312107086182,
      "learning_rate": 0.00019975141040730207,
      "loss": 1.0652,
      "step": 21
    },
    {
      "epoch": 0.006212495587716202,
      "grad_norm": 0.9025612473487854,
      "learning_rate": 0.0001997041811497882,
      "loss": 1.9069,
      "step": 22
    },
    {
      "epoch": 0.006494881750794211,
      "grad_norm": 0.662822961807251,
      "learning_rate": 0.00019965285344390184,
      "loss": 2.1184,
      "step": 23
    },
    {
      "epoch": 0.00677726791387222,
      "grad_norm": 1.2998898029327393,
      "learning_rate": 0.00019959742939952392,
      "loss": 1.3041,
      "step": 24
    },
    {
      "epoch": 0.0070596540769502295,
      "grad_norm": 0.87566077709198,
      "learning_rate": 0.00019953791129491983,
      "loss": 1.8995,
      "step": 25
    },
    {
      "epoch": 0.007342040240028239,
      "grad_norm": 1.7948976755142212,
      "learning_rate": 0.00019947430157664576,
      "loss": 1.0098,
      "step": 26
    },
    {
      "epoch": 0.007624426403106248,
      "grad_norm": 0.8442519307136536,
      "learning_rate": 0.00019940660285944803,
      "loss": 1.9566,
      "step": 27
    },
    {
      "epoch": 0.007906812566184257,
      "grad_norm": 1.40757155418396,
      "learning_rate": 0.00019933481792615583,
      "loss": 1.6962,
      "step": 28
    },
    {
      "epoch": 0.008189198729262267,
      "grad_norm": 1.3247369527816772,
      "learning_rate": 0.0001992589497275665,
      "loss": 1.6803,
      "step": 29
    },
    {
      "epoch": 0.008471584892340275,
      "grad_norm": 2.1888298988342285,
      "learning_rate": 0.0001991790013823246,
      "loss": 1.1217,
      "step": 30
    },
    {
      "epoch": 0.008471584892340275,
      "eval_loss": 1.3264524936676025,
      "eval_runtime": 422.0198,
      "eval_samples_per_second": 1.768,
      "eval_steps_per_second": 1.768,
      "step": 30
    },
    {
      "epoch": 0.008753971055418284,
      "grad_norm": 0.716585636138916,
      "learning_rate": 0.00019909497617679348,
      "loss": 2.0163,
      "step": 31
    },
    {
      "epoch": 0.009036357218496294,
      "grad_norm": 1.1441899538040161,
      "learning_rate": 0.0001990068775649202,
      "loss": 1.9939,
      "step": 32
    },
    {
      "epoch": 0.009318743381574303,
      "grad_norm": 0.9873970746994019,
      "learning_rate": 0.00019891470916809362,
      "loss": 2.0328,
      "step": 33
    },
    {
      "epoch": 0.009601129544652313,
      "grad_norm": 1.0919432640075684,
      "learning_rate": 0.00019881847477499557,
      "loss": 1.4307,
      "step": 34
    },
    {
      "epoch": 0.009883515707730321,
      "grad_norm": 1.9606109857559204,
      "learning_rate": 0.00019871817834144504,
      "loss": 0.8573,
      "step": 35
    },
    {
      "epoch": 0.01016590187080833,
      "grad_norm": 0.7053022384643555,
      "learning_rate": 0.0001986138239902355,
      "loss": 1.7692,
      "step": 36
    },
    {
      "epoch": 0.01044828803388634,
      "grad_norm": 1.2274115085601807,
      "learning_rate": 0.0001985054160109657,
      "loss": 1.3894,
      "step": 37
    },
    {
      "epoch": 0.010730674196964348,
      "grad_norm": 0.6820394992828369,
      "learning_rate": 0.00019839295885986296,
      "loss": 1.4337,
      "step": 38
    },
    {
      "epoch": 0.011013060360042359,
      "grad_norm": 1.0677088499069214,
      "learning_rate": 0.0001982764571596004,
      "loss": 1.6154,
      "step": 39
    },
    {
      "epoch": 0.011295446523120367,
      "grad_norm": 1.6393396854400635,
      "learning_rate": 0.00019815591569910654,
      "loss": 2.0251,
      "step": 40
    },
    {
      "epoch": 0.011295446523120367,
      "eval_loss": 1.3246878385543823,
      "eval_runtime": 422.1745,
      "eval_samples_per_second": 1.767,
      "eval_steps_per_second": 1.767,
      "step": 40
    },
    {
      "epoch": 0.011577832686198376,
      "grad_norm": 1.3773140907287598,
      "learning_rate": 0.00019803133943336874,
      "loss": 1.7091,
      "step": 41
    },
    {
      "epoch": 0.011860218849276386,
      "grad_norm": 0.8763225078582764,
      "learning_rate": 0.0001979027334832293,
      "loss": 1.7084,
      "step": 42
    },
    {
      "epoch": 0.012142605012354394,
      "grad_norm": 0.8546161651611328,
      "learning_rate": 0.00019777010313517518,
      "loss": 1.7023,
      "step": 43
    },
    {
      "epoch": 0.012424991175432405,
      "grad_norm": 2.4073739051818848,
      "learning_rate": 0.00019763345384112043,
      "loss": 1.1566,
      "step": 44
    },
    {
      "epoch": 0.012707377338510413,
      "grad_norm": 1.2686834335327148,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.3033,
      "step": 45
    },
    {
      "epoch": 0.012989763501588421,
      "grad_norm": 0.7953050136566162,
      "learning_rate": 0.00019734812104845047,
      "loss": 1.5463,
      "step": 46
    },
    {
      "epoch": 0.013272149664666432,
      "grad_norm": 1.074453592300415,
      "learning_rate": 0.00019719944927874881,
      "loss": 1.5074,
      "step": 47
    },
    {
      "epoch": 0.01355453582774444,
      "grad_norm": 1.1829779148101807,
      "learning_rate": 0.0001970467820203915,
      "loss": 1.2887,
      "step": 48
    },
    {
      "epoch": 0.01383692199082245,
      "grad_norm": 0.631193995475769,
      "learning_rate": 0.00019689012554893154,
      "loss": 1.614,
      "step": 49
    },
    {
      "epoch": 0.014119308153900459,
      "grad_norm": 0.6255627274513245,
      "learning_rate": 0.00019672948630390294,
      "loss": 0.7312,
      "step": 50
    },
    {
      "epoch": 0.014119308153900459,
      "eval_loss": 1.303961157798767,
      "eval_runtime": 420.1974,
      "eval_samples_per_second": 1.775,
      "eval_steps_per_second": 1.775,
      "step": 50
    },
    {
      "epoch": 0.014401694316978467,
      "grad_norm": 1.264630913734436,
      "learning_rate": 0.00019656487088855592,
      "loss": 1.1731,
      "step": 51
    },
    {
      "epoch": 0.014684080480056478,
      "grad_norm": 1.3137420415878296,
      "learning_rate": 0.00019639628606958533,
      "loss": 0.795,
      "step": 52
    },
    {
      "epoch": 0.014966466643134486,
      "grad_norm": 1.4407997131347656,
      "learning_rate": 0.0001962237387768529,
      "loss": 1.3326,
      "step": 53
    },
    {
      "epoch": 0.015248852806212496,
      "grad_norm": 1.2762479782104492,
      "learning_rate": 0.00019604723610310194,
      "loss": 0.7972,
      "step": 54
    },
    {
      "epoch": 0.015531238969290505,
      "grad_norm": 1.0771076679229736,
      "learning_rate": 0.00019586678530366606,
      "loss": 1.3158,
      "step": 55
    },
    {
      "epoch": 0.015813625132368513,
      "grad_norm": 0.8992990851402283,
      "learning_rate": 0.00019568239379617088,
      "loss": 1.4787,
      "step": 56
    },
    {
      "epoch": 0.016096011295446522,
      "grad_norm": 1.2085480690002441,
      "learning_rate": 0.00019549406916022905,
      "loss": 1.3324,
      "step": 57
    },
    {
      "epoch": 0.016378397458524534,
      "grad_norm": 0.7203757166862488,
      "learning_rate": 0.00019530181913712872,
      "loss": 1.548,
      "step": 58
    },
    {
      "epoch": 0.016660783621602542,
      "grad_norm": 1.4223425388336182,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.8365,
      "step": 59
    },
    {
      "epoch": 0.01694316978468055,
      "grad_norm": 0.46909332275390625,
      "learning_rate": 0.00019490557470106686,
      "loss": 1.6222,
      "step": 60
    },
    {
      "epoch": 0.01694316978468055,
      "eval_loss": 1.3196920156478882,
      "eval_runtime": 419.9731,
      "eval_samples_per_second": 1.776,
      "eval_steps_per_second": 1.776,
      "step": 60
    },
    {
      "epoch": 0.01722555594775856,
      "grad_norm": 0.7459226846694946,
      "learning_rate": 0.00019470159657616215,
      "loss": 1.4639,
      "step": 61
    },
    {
      "epoch": 0.017507942110836568,
      "grad_norm": 1.4355456829071045,
      "learning_rate": 0.00019449372563954293,
      "loss": 1.4994,
      "step": 62
    },
    {
      "epoch": 0.01779032827391458,
      "grad_norm": 0.7244583964347839,
      "learning_rate": 0.0001942819704359693,
      "loss": 0.3904,
      "step": 63
    },
    {
      "epoch": 0.018072714436992588,
      "grad_norm": 0.9388204216957092,
      "learning_rate": 0.00019406633966986828,
      "loss": 1.8876,
      "step": 64
    },
    {
      "epoch": 0.018355100600070597,
      "grad_norm": 2.272127866744995,
      "learning_rate": 0.00019384684220497605,
      "loss": 1.5339,
      "step": 65
    },
    {
      "epoch": 0.018637486763148605,
      "grad_norm": 0.8985967636108398,
      "learning_rate": 0.00019362348706397373,
      "loss": 1.5562,
      "step": 66
    },
    {
      "epoch": 0.018919872926226614,
      "grad_norm": 1.5650131702423096,
      "learning_rate": 0.00019339628342811632,
      "loss": 0.6815,
      "step": 67
    },
    {
      "epoch": 0.019202259089304625,
      "grad_norm": 1.2985599040985107,
      "learning_rate": 0.0001931652406368554,
      "loss": 0.8239,
      "step": 68
    },
    {
      "epoch": 0.019484645252382634,
      "grad_norm": 1.2683568000793457,
      "learning_rate": 0.0001929303681874552,
      "loss": 1.6103,
      "step": 69
    },
    {
      "epoch": 0.019767031415460642,
      "grad_norm": 1.2072068452835083,
      "learning_rate": 0.0001926916757346022,
      "loss": 2.0554,
      "step": 70
    },
    {
      "epoch": 0.019767031415460642,
      "eval_loss": 1.293800711631775,
      "eval_runtime": 418.574,
      "eval_samples_per_second": 1.782,
      "eval_steps_per_second": 1.782,
      "step": 70
    },
    {
      "epoch": 0.02004941757853865,
      "grad_norm": 1.6358360052108765,
      "learning_rate": 0.00019244917309000817,
      "loss": 1.3294,
      "step": 71
    },
    {
      "epoch": 0.02033180374161666,
      "grad_norm": 1.2779337167739868,
      "learning_rate": 0.00019220287022200707,
      "loss": 1.4654,
      "step": 72
    },
    {
      "epoch": 0.02061418990469467,
      "grad_norm": 1.0031236410140991,
      "learning_rate": 0.0001919527772551451,
      "loss": 1.4763,
      "step": 73
    },
    {
      "epoch": 0.02089657606777268,
      "grad_norm": 1.0776865482330322,
      "learning_rate": 0.00019169890446976454,
      "loss": 1.9505,
      "step": 74
    },
    {
      "epoch": 0.02117896223085069,
      "grad_norm": 1.0557630062103271,
      "learning_rate": 0.00019144126230158127,
      "loss": 1.425,
      "step": 75
    },
    {
      "epoch": 0.021461348393928697,
      "grad_norm": 1.4582068920135498,
      "learning_rate": 0.0001911798613412557,
      "loss": 2.1393,
      "step": 76
    },
    {
      "epoch": 0.021743734557006705,
      "grad_norm": 0.8082997798919678,
      "learning_rate": 0.0001909147123339575,
      "loss": 1.94,
      "step": 77
    },
    {
      "epoch": 0.022026120720084717,
      "grad_norm": 0.6186602711677551,
      "learning_rate": 0.0001906458261789238,
      "loss": 2.4405,
      "step": 78
    },
    {
      "epoch": 0.022308506883162726,
      "grad_norm": 0.9546780586242676,
      "learning_rate": 0.00019037321392901136,
      "loss": 1.4176,
      "step": 79
    },
    {
      "epoch": 0.022590893046240734,
      "grad_norm": 0.5143202543258667,
      "learning_rate": 0.0001900968867902419,
      "loss": 2.0072,
      "step": 80
    },
    {
      "epoch": 0.022590893046240734,
      "eval_loss": 1.2894105911254883,
      "eval_runtime": 419.1859,
      "eval_samples_per_second": 1.78,
      "eval_steps_per_second": 1.78,
      "step": 80
    },
    {
      "epoch": 0.022873279209318743,
      "grad_norm": 0.835146963596344,
      "learning_rate": 0.0001898168561213419,
      "loss": 1.6153,
      "step": 81
    },
    {
      "epoch": 0.02315566537239675,
      "grad_norm": 0.6441218852996826,
      "learning_rate": 0.0001895331334332753,
      "loss": 1.3453,
      "step": 82
    },
    {
      "epoch": 0.023438051535474763,
      "grad_norm": 1.0550341606140137,
      "learning_rate": 0.0001892457303887706,
      "loss": 0.7759,
      "step": 83
    },
    {
      "epoch": 0.02372043769855277,
      "grad_norm": 1.1421196460723877,
      "learning_rate": 0.0001889546588018412,
      "loss": 1.4067,
      "step": 84
    },
    {
      "epoch": 0.02400282386163078,
      "grad_norm": 0.683531641960144,
      "learning_rate": 0.00018865993063730004,
      "loss": 2.1907,
      "step": 85
    },
    {
      "epoch": 0.02428521002470879,
      "grad_norm": 1.0629582405090332,
      "learning_rate": 0.00018836155801026753,
      "loss": 1.656,
      "step": 86
    },
    {
      "epoch": 0.024567596187786797,
      "grad_norm": 1.9884428977966309,
      "learning_rate": 0.0001880595531856738,
      "loss": 1.3818,
      "step": 87
    },
    {
      "epoch": 0.02484998235086481,
      "grad_norm": 0.8152889013290405,
      "learning_rate": 0.00018775392857775432,
      "loss": 2.4539,
      "step": 88
    },
    {
      "epoch": 0.025132368513942818,
      "grad_norm": 1.8213200569152832,
      "learning_rate": 0.00018744469674953956,
      "loss": 0.8031,
      "step": 89
    },
    {
      "epoch": 0.025414754677020826,
      "grad_norm": 1.3625519275665283,
      "learning_rate": 0.00018713187041233896,
      "loss": 1.5481,
      "step": 90
    },
    {
      "epoch": 0.025414754677020826,
      "eval_loss": 1.2990045547485352,
      "eval_runtime": 420.4752,
      "eval_samples_per_second": 1.774,
      "eval_steps_per_second": 1.774,
      "step": 90
    },
    {
      "epoch": 0.025697140840098835,
      "grad_norm": 0.922839343547821,
      "learning_rate": 0.00018681546242521786,
      "loss": 2.2968,
      "step": 91
    },
    {
      "epoch": 0.025979527003176843,
      "grad_norm": 0.9457669258117676,
      "learning_rate": 0.00018649548579446936,
      "loss": 1.5159,
      "step": 92
    },
    {
      "epoch": 0.026261913166254855,
      "grad_norm": 1.3212480545043945,
      "learning_rate": 0.0001861719536730795,
      "loss": 1.8084,
      "step": 93
    },
    {
      "epoch": 0.026544299329332863,
      "grad_norm": 1.1744962930679321,
      "learning_rate": 0.00018584487936018661,
      "loss": 2.3983,
      "step": 94
    },
    {
      "epoch": 0.026826685492410872,
      "grad_norm": 0.9709725379943848,
      "learning_rate": 0.00018551427630053463,
      "loss": 1.8034,
      "step": 95
    },
    {
      "epoch": 0.02710907165548888,
      "grad_norm": 0.878976047039032,
      "learning_rate": 0.00018518015808392045,
      "loss": 1.2276,
      "step": 96
    },
    {
      "epoch": 0.02739145781856689,
      "grad_norm": 1.220984935760498,
      "learning_rate": 0.00018484253844463526,
      "loss": 1.0919,
      "step": 97
    },
    {
      "epoch": 0.0276738439816449,
      "grad_norm": 0.41714727878570557,
      "learning_rate": 0.00018450143126090015,
      "loss": 1.0902,
      "step": 98
    },
    {
      "epoch": 0.02795623014472291,
      "grad_norm": 0.9148246049880981,
      "learning_rate": 0.00018415685055429533,
      "loss": 2.1429,
      "step": 99
    },
    {
      "epoch": 0.028238616307800918,
      "grad_norm": 0.8029168844223022,
      "learning_rate": 0.00018380881048918405,
      "loss": 1.5813,
      "step": 100
    },
    {
      "epoch": 0.028238616307800918,
      "eval_loss": 1.3071253299713135,
      "eval_runtime": 421.1658,
      "eval_samples_per_second": 1.771,
      "eval_steps_per_second": 1.771,
      "step": 100
    },
    {
      "epoch": 0.028521002470878926,
      "grad_norm": 0.8574671745300293,
      "learning_rate": 0.00018345732537213027,
      "loss": 1.9177,
      "step": 101
    },
    {
      "epoch": 0.028803388633956935,
      "grad_norm": 0.9129525423049927,
      "learning_rate": 0.00018310240965131041,
      "loss": 2.4622,
      "step": 102
    },
    {
      "epoch": 0.029085774797034947,
      "grad_norm": 0.8835414052009583,
      "learning_rate": 0.00018274407791591966,
      "loss": 1.051,
      "step": 103
    },
    {
      "epoch": 0.029368160960112955,
      "grad_norm": 0.508120059967041,
      "learning_rate": 0.00018238234489557215,
      "loss": 0.4317,
      "step": 104
    },
    {
      "epoch": 0.029650547123190964,
      "grad_norm": 1.259400725364685,
      "learning_rate": 0.0001820172254596956,
      "loss": 1.9737,
      "step": 105
    },
    {
      "epoch": 0.029932933286268972,
      "grad_norm": 1.45259428024292,
      "learning_rate": 0.00018164873461691986,
      "loss": 0.6959,
      "step": 106
    },
    {
      "epoch": 0.03021531944934698,
      "grad_norm": 0.8846643567085266,
      "learning_rate": 0.00018127688751446027,
      "loss": 1.3487,
      "step": 107
    },
    {
      "epoch": 0.030497705612424993,
      "grad_norm": 0.7302697896957397,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.7445,
      "step": 108
    },
    {
      "epoch": 0.030780091775503,
      "grad_norm": 1.3288211822509766,
      "learning_rate": 0.0001805231858085356,
      "loss": 1.2461,
      "step": 109
    },
    {
      "epoch": 0.03106247793858101,
      "grad_norm": 0.4046940207481384,
      "learning_rate": 0.00018014136218679567,
      "loss": 1.9418,
      "step": 110
    },
    {
      "epoch": 0.03106247793858101,
      "eval_loss": 1.3085497617721558,
      "eval_runtime": 418.6203,
      "eval_samples_per_second": 1.782,
      "eval_steps_per_second": 1.782,
      "step": 110
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.206114973810688e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}