{
  "best_metric": 1.9069808721542358,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.11590843233845262,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011590843233845263,
      "grad_norm": 0.5617161989212036,
      "learning_rate": 7e-06,
      "loss": 2.0317,
      "step": 1
    },
    {
      "epoch": 0.0011590843233845263,
      "eval_loss": 2.8248138427734375,
      "eval_runtime": 101.3167,
      "eval_samples_per_second": 14.341,
      "eval_steps_per_second": 3.593,
      "step": 1
    },
    {
      "epoch": 0.0023181686467690526,
      "grad_norm": 0.8308987617492676,
      "learning_rate": 1.4e-05,
      "loss": 1.8377,
      "step": 2
    },
    {
      "epoch": 0.0034772529701535787,
      "grad_norm": 0.7668841481208801,
      "learning_rate": 2.1e-05,
      "loss": 2.1166,
      "step": 3
    },
    {
      "epoch": 0.004636337293538105,
      "grad_norm": 0.7772699594497681,
      "learning_rate": 2.8e-05,
      "loss": 2.3383,
      "step": 4
    },
    {
      "epoch": 0.005795421616922631,
      "grad_norm": 0.8564109206199646,
      "learning_rate": 3.5e-05,
      "loss": 2.247,
      "step": 5
    },
    {
      "epoch": 0.006954505940307157,
      "grad_norm": 0.9142338037490845,
      "learning_rate": 4.2e-05,
      "loss": 2.0694,
      "step": 6
    },
    {
      "epoch": 0.008113590263691683,
      "grad_norm": 0.9802976846694946,
      "learning_rate": 4.899999999999999e-05,
      "loss": 2.1744,
      "step": 7
    },
    {
      "epoch": 0.00927267458707621,
      "grad_norm": 0.9551035761833191,
      "learning_rate": 5.6e-05,
      "loss": 1.9839,
      "step": 8
    },
    {
      "epoch": 0.010431758910460736,
      "grad_norm": 1.0417977571487427,
      "learning_rate": 6.3e-05,
      "loss": 2.0927,
      "step": 9
    },
    {
      "epoch": 0.011590843233845263,
      "grad_norm": 0.8984870910644531,
      "learning_rate": 7e-05,
      "loss": 1.8616,
      "step": 10
    },
    {
      "epoch": 0.012749927557229788,
      "grad_norm": 0.8334612846374512,
      "learning_rate": 6.999521567473641e-05,
      "loss": 1.9348,
      "step": 11
    },
    {
      "epoch": 0.013909011880614315,
      "grad_norm": 1.0292818546295166,
      "learning_rate": 6.998086400693241e-05,
      "loss": 2.0118,
      "step": 12
    },
    {
      "epoch": 0.015068096203998842,
      "grad_norm": 0.9132320880889893,
      "learning_rate": 6.995694892019065e-05,
      "loss": 1.7204,
      "step": 13
    },
    {
      "epoch": 0.016227180527383367,
      "grad_norm": 0.9421163201332092,
      "learning_rate": 6.99234769526571e-05,
      "loss": 1.9112,
      "step": 14
    },
    {
      "epoch": 0.017386264850767892,
      "grad_norm": 1.0101693868637085,
      "learning_rate": 6.988045725523343e-05,
      "loss": 1.6642,
      "step": 15
    },
    {
      "epoch": 0.01854534917415242,
      "grad_norm": 1.0200189352035522,
      "learning_rate": 6.982790158907539e-05,
      "loss": 1.8958,
      "step": 16
    },
    {
      "epoch": 0.019704433497536946,
      "grad_norm": 1.120744228363037,
      "learning_rate": 6.976582432237733e-05,
      "loss": 1.8165,
      "step": 17
    },
    {
      "epoch": 0.02086351782092147,
      "grad_norm": 1.001584529876709,
      "learning_rate": 6.969424242644413e-05,
      "loss": 1.8139,
      "step": 18
    },
    {
      "epoch": 0.022022602144306,
      "grad_norm": 0.9849500060081482,
      "learning_rate": 6.961317547105138e-05,
      "loss": 1.7734,
      "step": 19
    },
    {
      "epoch": 0.023181686467690525,
      "grad_norm": 0.9495387673377991,
      "learning_rate": 6.952264561909527e-05,
      "loss": 1.5883,
      "step": 20
    },
    {
      "epoch": 0.02434077079107505,
      "grad_norm": 1.0540260076522827,
      "learning_rate": 6.942267762053337e-05,
      "loss": 1.8574,
      "step": 21
    },
    {
      "epoch": 0.025499855114459576,
      "grad_norm": 0.9781659841537476,
      "learning_rate": 6.931329880561832e-05,
      "loss": 1.6139,
      "step": 22
    },
    {
      "epoch": 0.026658939437844104,
      "grad_norm": 0.9468351602554321,
      "learning_rate": 6.919453907742597e-05,
      "loss": 1.7195,
      "step": 23
    },
    {
      "epoch": 0.02781802376122863,
      "grad_norm": 1.0345453023910522,
      "learning_rate": 6.90664309036802e-05,
      "loss": 1.9237,
      "step": 24
    },
    {
      "epoch": 0.028977108084613155,
      "grad_norm": 1.0196911096572876,
      "learning_rate": 6.892900930787656e-05,
      "loss": 1.8853,
      "step": 25
    },
    {
      "epoch": 0.030136192407997683,
      "grad_norm": 1.1035205125808716,
      "learning_rate": 6.87823118597072e-05,
      "loss": 1.7198,
      "step": 26
    },
    {
      "epoch": 0.03129527673138221,
      "grad_norm": 1.0238853693008423,
      "learning_rate": 6.862637866478969e-05,
      "loss": 1.8854,
      "step": 27
    },
    {
      "epoch": 0.032454361054766734,
      "grad_norm": 1.1377280950546265,
      "learning_rate": 6.846125235370252e-05,
      "loss": 2.0783,
      "step": 28
    },
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 1.3032432794570923,
      "learning_rate": 6.828697807033038e-05,
      "loss": 2.0572,
      "step": 29
    },
    {
      "epoch": 0.034772529701535784,
      "grad_norm": 1.033238172531128,
      "learning_rate": 6.81036034595222e-05,
      "loss": 1.7329,
      "step": 30
    },
    {
      "epoch": 0.035931614024920316,
      "grad_norm": 1.0275241136550903,
      "learning_rate": 6.791117865406564e-05,
      "loss": 1.682,
      "step": 31
    },
    {
      "epoch": 0.03709069834830484,
      "grad_norm": 1.0417641401290894,
      "learning_rate": 6.770975626098112e-05,
      "loss": 1.9175,
      "step": 32
    },
    {
      "epoch": 0.03824978267168937,
      "grad_norm": 1.2844064235687256,
      "learning_rate": 6.749939134713974e-05,
      "loss": 2.0107,
      "step": 33
    },
    {
      "epoch": 0.03940886699507389,
      "grad_norm": 1.2008929252624512,
      "learning_rate": 6.728014142420846e-05,
      "loss": 1.9569,
      "step": 34
    },
    {
      "epoch": 0.04056795131845842,
      "grad_norm": 1.2086220979690552,
      "learning_rate": 6.7052066432927e-05,
      "loss": 2.0818,
      "step": 35
    },
    {
      "epoch": 0.04172703564184294,
      "grad_norm": 1.1457483768463135,
      "learning_rate": 6.681522872672069e-05,
      "loss": 2.002,
      "step": 36
    },
    {
      "epoch": 0.04288611996522747,
      "grad_norm": 1.1261320114135742,
      "learning_rate": 6.656969305465356e-05,
      "loss": 1.7857,
      "step": 37
    },
    {
      "epoch": 0.044045204288612,
      "grad_norm": 1.1614913940429688,
      "learning_rate": 6.631552654372672e-05,
      "loss": 1.9917,
      "step": 38
    },
    {
      "epoch": 0.045204288611996525,
      "grad_norm": 1.1968772411346436,
      "learning_rate": 6.60527986805264e-05,
      "loss": 1.9252,
      "step": 39
    },
    {
      "epoch": 0.04636337293538105,
      "grad_norm": 1.3660227060317993,
      "learning_rate": 6.578158129222711e-05,
      "loss": 2.0329,
      "step": 40
    },
    {
      "epoch": 0.047522457258765576,
      "grad_norm": 1.332165241241455,
      "learning_rate": 6.550194852695469e-05,
      "loss": 2.1746,
      "step": 41
    },
    {
      "epoch": 0.0486815415821501,
      "grad_norm": 1.243107557296753,
      "learning_rate": 6.521397683351509e-05,
      "loss": 2.0625,
      "step": 42
    },
    {
      "epoch": 0.049840625905534626,
      "grad_norm": 1.33090341091156,
      "learning_rate": 6.491774494049386e-05,
      "loss": 2.2343,
      "step": 43
    },
    {
      "epoch": 0.05099971022891915,
      "grad_norm": 1.3284821510314941,
      "learning_rate": 6.461333383473272e-05,
      "loss": 1.9925,
      "step": 44
    },
    {
      "epoch": 0.05215879455230368,
      "grad_norm": 1.4600505828857422,
      "learning_rate": 6.430082673918849e-05,
      "loss": 1.8349,
      "step": 45
    },
    {
      "epoch": 0.05331787887568821,
      "grad_norm": 1.3876497745513916,
      "learning_rate": 6.398030909018069e-05,
      "loss": 1.8771,
      "step": 46
    },
    {
      "epoch": 0.054476963199072734,
      "grad_norm": 1.5812242031097412,
      "learning_rate": 6.365186851403423e-05,
      "loss": 2.1935,
      "step": 47
    },
    {
      "epoch": 0.05563604752245726,
      "grad_norm": 1.8776988983154297,
      "learning_rate": 6.331559480312315e-05,
      "loss": 2.2423,
      "step": 48
    },
    {
      "epoch": 0.056795131845841784,
      "grad_norm": 1.9295244216918945,
      "learning_rate": 6.297157989132236e-05,
      "loss": 2.339,
      "step": 49
    },
    {
      "epoch": 0.05795421616922631,
      "grad_norm": 3.2445361614227295,
      "learning_rate": 6.261991782887377e-05,
      "loss": 2.8354,
      "step": 50
    },
    {
      "epoch": 0.05795421616922631,
      "eval_loss": 2.070936918258667,
      "eval_runtime": 103.0085,
      "eval_samples_per_second": 14.106,
      "eval_steps_per_second": 3.534,
      "step": 50
    },
    {
      "epoch": 0.059113300492610835,
      "grad_norm": 2.1962857246398926,
      "learning_rate": 6.226070475667393e-05,
      "loss": 1.749,
      "step": 51
    },
    {
      "epoch": 0.06027238481599537,
      "grad_norm": 2.2130725383758545,
      "learning_rate": 6.189403887999006e-05,
      "loss": 1.6955,
      "step": 52
    },
    {
      "epoch": 0.06143146913937989,
      "grad_norm": 1.676161766052246,
      "learning_rate": 6.152002044161171e-05,
      "loss": 1.8295,
      "step": 53
    },
    {
      "epoch": 0.06259055346276442,
      "grad_norm": 1.1914523839950562,
      "learning_rate": 6.113875169444539e-05,
      "loss": 1.869,
      "step": 54
    },
    {
      "epoch": 0.06374963778614894,
      "grad_norm": 0.9858117699623108,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 1.9403,
      "step": 55
    },
    {
      "epoch": 0.06490872210953347,
      "grad_norm": 0.93446284532547,
      "learning_rate": 6.035488216768811e-05,
      "loss": 1.7909,
      "step": 56
    },
    {
      "epoch": 0.066067806432918,
      "grad_norm": 0.7381186485290527,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 1.5857,
      "step": 57
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.8235486149787903,
      "learning_rate": 5.954328744953709e-05,
      "loss": 1.7983,
      "step": 58
    },
    {
      "epoch": 0.06838597507968705,
      "grad_norm": 0.7572500109672546,
      "learning_rate": 5.91273693191498e-05,
      "loss": 1.6261,
      "step": 59
    },
    {
      "epoch": 0.06954505940307157,
      "grad_norm": 0.9166513085365295,
      "learning_rate": 5.870485500690094e-05,
      "loss": 1.8126,
      "step": 60
    },
    {
      "epoch": 0.0707041437264561,
      "grad_norm": 0.887972354888916,
      "learning_rate": 5.827586002398468e-05,
      "loss": 1.6087,
      "step": 61
    },
    {
      "epoch": 0.07186322804984063,
      "grad_norm": 0.817246675491333,
      "learning_rate": 5.784050165334589e-05,
      "loss": 1.8542,
      "step": 62
    },
    {
      "epoch": 0.07302231237322515,
      "grad_norm": 1.115594506263733,
      "learning_rate": 5.739889891761608e-05,
      "loss": 1.5087,
      "step": 63
    },
    {
      "epoch": 0.07418139669660968,
      "grad_norm": 0.8168441653251648,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 1.6609,
      "step": 64
    },
    {
      "epoch": 0.0753404810199942,
      "grad_norm": 0.9525291919708252,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 1.9454,
      "step": 65
    },
    {
      "epoch": 0.07649956534337873,
      "grad_norm": 0.943900465965271,
      "learning_rate": 5.603784015490587e-05,
      "loss": 1.6792,
      "step": 66
    },
    {
      "epoch": 0.07765864966676325,
      "grad_norm": 0.9026935696601868,
      "learning_rate": 5.557248383023655e-05,
      "loss": 1.7305,
      "step": 67
    },
    {
      "epoch": 0.07881773399014778,
      "grad_norm": 0.9322032332420349,
      "learning_rate": 5.510150319390302e-05,
      "loss": 1.7397,
      "step": 68
    },
    {
      "epoch": 0.07997681831353232,
      "grad_norm": 0.8686115145683289,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 1.7237,
      "step": 69
    },
    {
      "epoch": 0.08113590263691683,
      "grad_norm": 0.9351975321769714,
      "learning_rate": 5.414318553428494e-05,
      "loss": 1.8886,
      "step": 70
    },
    {
      "epoch": 0.08229498696030137,
      "grad_norm": 0.974967360496521,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 1.9276,
      "step": 71
    },
    {
      "epoch": 0.08345407128368589,
      "grad_norm": 0.9757768511772156,
      "learning_rate": 5.316393508234253e-05,
      "loss": 1.9968,
      "step": 72
    },
    {
      "epoch": 0.08461315560707042,
      "grad_norm": 1.1062190532684326,
      "learning_rate": 5.266679382071953e-05,
      "loss": 1.5988,
      "step": 73
    },
    {
      "epoch": 0.08577223993045494,
      "grad_norm": 0.9316264390945435,
      "learning_rate": 5.216482263406778e-05,
      "loss": 1.9706,
      "step": 74
    },
    {
      "epoch": 0.08693132425383947,
      "grad_norm": 0.9845229983329773,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 1.8155,
      "step": 75
    },
    {
      "epoch": 0.088090408577224,
      "grad_norm": 1.0393840074539185,
      "learning_rate": 5.114694070425407e-05,
      "loss": 1.9335,
      "step": 76
    },
    {
      "epoch": 0.08924949290060852,
      "grad_norm": 1.023858666419983,
      "learning_rate": 5.063130823984823e-05,
      "loss": 1.9187,
      "step": 77
    },
    {
      "epoch": 0.09040857722399305,
      "grad_norm": 0.8370853066444397,
      "learning_rate": 5.011140233184724e-05,
      "loss": 1.7654,
      "step": 78
    },
    {
      "epoch": 0.09156766154737757,
      "grad_norm": 1.108378529548645,
      "learning_rate": 4.958736511733516e-05,
      "loss": 1.7187,
      "step": 79
    },
    {
      "epoch": 0.0927267458707621,
      "grad_norm": 1.0803954601287842,
      "learning_rate": 4.905933986285393e-05,
      "loss": 1.8403,
      "step": 80
    },
    {
      "epoch": 0.09388583019414662,
      "grad_norm": 0.8947066068649292,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 1.888,
      "step": 81
    },
    {
      "epoch": 0.09504491451753115,
      "grad_norm": 1.0540757179260254,
      "learning_rate": 4.799190371213772e-05,
      "loss": 1.8883,
      "step": 82
    },
    {
      "epoch": 0.09620399884091568,
      "grad_norm": 0.9781203866004944,
      "learning_rate": 4.745278464228808e-05,
      "loss": 1.8643,
      "step": 83
    },
    {
      "epoch": 0.0973630831643002,
      "grad_norm": 0.9711923599243164,
      "learning_rate": 4.69102611054575e-05,
      "loss": 1.8855,
      "step": 84
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 1.0181244611740112,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 1.9491,
      "step": 85
    },
    {
      "epoch": 0.09968125181106925,
      "grad_norm": 1.0562760829925537,
      "learning_rate": 4.581559480312316e-05,
      "loss": 1.7729,
      "step": 86
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 1.028149127960205,
      "learning_rate": 4.526375130845627e-05,
      "loss": 1.8674,
      "step": 87
    },
    {
      "epoch": 0.1019994204578383,
      "grad_norm": 1.125438928604126,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 2.0341,
      "step": 88
    },
    {
      "epoch": 0.10315850478122283,
      "grad_norm": 1.123214602470398,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 2.117,
      "step": 89
    },
    {
      "epoch": 0.10431758910460737,
      "grad_norm": 1.0544837713241577,
      "learning_rate": 4.359199204992797e-05,
      "loss": 1.9251,
      "step": 90
    },
    {
      "epoch": 0.10547667342799188,
      "grad_norm": 1.189324140548706,
      "learning_rate": 4.30298372016363e-05,
      "loss": 2.0538,
      "step": 91
    },
    {
      "epoch": 0.10663575775137642,
      "grad_norm": 1.275004506111145,
      "learning_rate": 4.246548707603114e-05,
      "loss": 1.9864,
      "step": 92
    },
    {
      "epoch": 0.10779484207476094,
      "grad_norm": 1.2068434953689575,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 1.9636,
      "step": 93
    },
    {
      "epoch": 0.10895392639814547,
      "grad_norm": 1.2466081380844116,
      "learning_rate": 4.133081870162385e-05,
      "loss": 2.1275,
      "step": 94
    },
    {
      "epoch": 0.11011301072152999,
      "grad_norm": 1.2089381217956543,
      "learning_rate": 4.076081065982569e-05,
      "loss": 2.2161,
      "step": 95
    },
    {
      "epoch": 0.11127209504491452,
      "grad_norm": 1.4395438432693481,
      "learning_rate": 4.018922766991447e-05,
      "loss": 2.0683,
      "step": 96
    },
    {
      "epoch": 0.11243117936829905,
      "grad_norm": 1.6649994850158691,
      "learning_rate": 3.961622599697241e-05,
      "loss": 2.2035,
      "step": 97
    },
    {
      "epoch": 0.11359026369168357,
      "grad_norm": 1.4525130987167358,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 2.411,
      "step": 98
    },
    {
      "epoch": 0.1147493480150681,
      "grad_norm": 1.8260668516159058,
      "learning_rate": 3.84665935587662e-05,
      "loss": 2.367,
      "step": 99
    },
    {
      "epoch": 0.11590843233845262,
      "grad_norm": 3.302351951599121,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 3.2636,
      "step": 100
    },
    {
      "epoch": 0.11590843233845262,
      "eval_loss": 1.9069808721542358,
      "eval_runtime": 102.9577,
      "eval_samples_per_second": 14.113,
      "eval_steps_per_second": 3.535,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.42188868534272e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}