{
  "best_metric": 0.636073112487793,
  "best_model_checkpoint": "miner_id_24/checkpoint-900",
  "epoch": 2.278893109061313,
  "eval_steps": 150,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002170374389582203,
      "eval_loss": 3.8393607139587402,
      "eval_runtime": 52.8023,
      "eval_samples_per_second": 14.715,
      "eval_steps_per_second": 1.856,
      "step": 1
    },
    {
      "epoch": 0.02170374389582203,
      "grad_norm": 26.712209701538086,
      "learning_rate": 6e-06,
      "loss": 10.3362,
      "step": 10
    },
    {
      "epoch": 0.04340748779164406,
      "grad_norm": 38.7980842590332,
      "learning_rate": 1.2e-05,
      "loss": 12.0151,
      "step": 20
    },
    {
      "epoch": 0.06511123168746609,
      "grad_norm": 29.304401397705078,
      "learning_rate": 1.8e-05,
      "loss": 11.2638,
      "step": 30
    },
    {
      "epoch": 0.08681497558328811,
      "grad_norm": 39.74540710449219,
      "learning_rate": 2.4e-05,
      "loss": 9.229,
      "step": 40
    },
    {
      "epoch": 0.10851871947911014,
      "grad_norm": 65.20191955566406,
      "learning_rate": 3e-05,
      "loss": 6.7067,
      "step": 50
    },
    {
      "epoch": 0.13022246337493218,
      "grad_norm": 15.829483985900879,
      "learning_rate": 2.9996479470277262e-05,
      "loss": 5.6606,
      "step": 60
    },
    {
      "epoch": 0.1519262072707542,
      "grad_norm": 16.72377586364746,
      "learning_rate": 2.9985919533659653e-05,
      "loss": 4.3456,
      "step": 70
    },
    {
      "epoch": 0.17362995116657623,
      "grad_norm": 17.048402786254883,
      "learning_rate": 2.9968325147023267e-05,
      "loss": 3.5431,
      "step": 80
    },
    {
      "epoch": 0.19533369506239825,
      "grad_norm": 23.174785614013672,
      "learning_rate": 2.994370456924292e-05,
      "loss": 3.5592,
      "step": 90
    },
    {
      "epoch": 0.21703743895822028,
      "grad_norm": 63.94609832763672,
      "learning_rate": 2.9912069357315394e-05,
      "loss": 3.5889,
      "step": 100
    },
    {
      "epoch": 0.23874118285404233,
      "grad_norm": 17.54082679748535,
      "learning_rate": 2.9873434360934543e-05,
      "loss": 4.0375,
      "step": 110
    },
    {
      "epoch": 0.26044492674986436,
      "grad_norm": 13.922243118286133,
      "learning_rate": 2.9827817715520775e-05,
      "loss": 3.5151,
      "step": 120
    },
    {
      "epoch": 0.2821486706456864,
      "grad_norm": 18.978328704833984,
      "learning_rate": 2.977524083370823e-05,
      "loss": 3.1774,
      "step": 130
    },
    {
      "epoch": 0.3038524145415084,
      "grad_norm": 19.49057388305664,
      "learning_rate": 2.9715728395293587e-05,
      "loss": 3.2158,
      "step": 140
    },
    {
      "epoch": 0.32555615843733043,
      "grad_norm": 36.420654296875,
      "learning_rate": 2.96493083356513e-05,
      "loss": 3.1129,
      "step": 150
    },
    {
      "epoch": 0.32555615843733043,
      "eval_loss": 0.803920328617096,
      "eval_runtime": 53.8173,
      "eval_samples_per_second": 14.438,
      "eval_steps_per_second": 1.821,
      "step": 150
    },
    {
      "epoch": 0.34725990233315246,
      "grad_norm": 15.815438270568848,
      "learning_rate": 2.9576011832620583e-05,
      "loss": 3.6763,
      "step": 160
    },
    {
      "epoch": 0.3689636462289745,
      "grad_norm": 17.322349548339844,
      "learning_rate": 2.9495873291870436e-05,
      "loss": 3.2852,
      "step": 170
    },
    {
      "epoch": 0.3906673901247965,
      "grad_norm": 16.479698181152344,
      "learning_rate": 2.940893033074948e-05,
      "loss": 3.0177,
      "step": 180
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 20.874675750732422,
      "learning_rate": 2.9315223760628224e-05,
      "loss": 2.676,
      "step": 190
    },
    {
      "epoch": 0.43407487791644056,
      "grad_norm": 29.774669647216797,
      "learning_rate": 2.9214797567742036e-05,
      "loss": 3.227,
      "step": 200
    },
    {
      "epoch": 0.45577862181226264,
      "grad_norm": 14.984698295593262,
      "learning_rate": 2.9107698892543862e-05,
      "loss": 3.4,
      "step": 210
    },
    {
      "epoch": 0.47748236570808467,
      "grad_norm": 18.93448829650879,
      "learning_rate": 2.8993978007576263e-05,
      "loss": 2.9846,
      "step": 220
    },
    {
      "epoch": 0.4991861096039067,
      "grad_norm": 17.96265411376953,
      "learning_rate": 2.8873688293873336e-05,
      "loss": 3.0037,
      "step": 230
    },
    {
      "epoch": 0.5208898534997287,
      "grad_norm": 23.578723907470703,
      "learning_rate": 2.874688621590339e-05,
      "loss": 2.7363,
      "step": 240
    },
    {
      "epoch": 0.5425935973955507,
      "grad_norm": 39.76424026489258,
      "learning_rate": 2.861363129506436e-05,
      "loss": 3.1817,
      "step": 250
    },
    {
      "epoch": 0.5642973412913728,
      "grad_norm": 20.42775535583496,
      "learning_rate": 2.847398608174417e-05,
      "loss": 3.2541,
      "step": 260
    },
    {
      "epoch": 0.5860010851871947,
      "grad_norm": 16.566482543945312,
      "learning_rate": 2.832801612595937e-05,
      "loss": 2.8651,
      "step": 270
    },
    {
      "epoch": 0.6077048290830168,
      "grad_norm": 16.73906707763672,
      "learning_rate": 2.8175789946585697e-05,
      "loss": 2.8237,
      "step": 280
    },
    {
      "epoch": 0.6294085729788389,
      "grad_norm": 23.292736053466797,
      "learning_rate": 2.801737899919502e-05,
      "loss": 3.0393,
      "step": 290
    },
    {
      "epoch": 0.6511123168746609,
      "grad_norm": 38.29425048828125,
      "learning_rate": 2.7852857642513838e-05,
      "loss": 2.7109,
      "step": 300
    },
    {
      "epoch": 0.6511123168746609,
      "eval_loss": 0.7168570756912231,
      "eval_runtime": 53.8613,
      "eval_samples_per_second": 14.426,
      "eval_steps_per_second": 1.819,
      "step": 300
    },
    {
      "epoch": 0.672816060770483,
      "grad_norm": 13.968533515930176,
      "learning_rate": 2.768230310351898e-05,
      "loss": 3.3938,
      "step": 310
    },
    {
      "epoch": 0.6945198046663049,
      "grad_norm": 16.265430450439453,
      "learning_rate": 2.7505795441186953e-05,
      "loss": 2.9047,
      "step": 320
    },
    {
      "epoch": 0.716223548562127,
      "grad_norm": 14.983628273010254,
      "learning_rate": 2.7323417508913973e-05,
      "loss": 2.7784,
      "step": 330
    },
    {
      "epoch": 0.737927292457949,
      "grad_norm": 20.370397567749023,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 2.7854,
      "step": 340
    },
    {
      "epoch": 0.759631036353771,
      "grad_norm": 50.72266387939453,
      "learning_rate": 2.6941395985584656e-05,
      "loss": 2.8735,
      "step": 350
    },
    {
      "epoch": 0.781334780249593,
      "grad_norm": 17.988285064697266,
      "learning_rate": 2.6741931716945336e-05,
      "loss": 3.0907,
      "step": 360
    },
    {
      "epoch": 0.8030385241454151,
      "grad_norm": 16.146488189697266,
      "learning_rate": 2.6536955739024436e-05,
      "loss": 2.7129,
      "step": 370
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 18.454801559448242,
      "learning_rate": 2.632656426835831e-05,
      "loss": 2.6485,
      "step": 380
    },
    {
      "epoch": 0.8464460119370592,
      "grad_norm": 19.638561248779297,
      "learning_rate": 2.6110856063537087e-05,
      "loss": 2.4677,
      "step": 390
    },
    {
      "epoch": 0.8681497558328811,
      "grad_norm": 35.427913665771484,
      "learning_rate": 2.5889932378846963e-05,
      "loss": 2.7575,
      "step": 400
    },
    {
      "epoch": 0.8898534997287032,
      "grad_norm": 17.886579513549805,
      "learning_rate": 2.5663896916741064e-05,
      "loss": 2.8667,
      "step": 410
    },
    {
      "epoch": 0.9115572436245253,
      "grad_norm": 17.810691833496094,
      "learning_rate": 2.543285577916108e-05,
      "loss": 2.7324,
      "step": 420
    },
    {
      "epoch": 0.9332609875203473,
      "grad_norm": 19.121427536010742,
      "learning_rate": 2.519691741773262e-05,
      "loss": 2.5549,
      "step": 430
    },
    {
      "epoch": 0.9549647314161693,
      "grad_norm": 21.621971130371094,
      "learning_rate": 2.495619258285757e-05,
      "loss": 2.4607,
      "step": 440
    },
    {
      "epoch": 0.9766684753119913,
      "grad_norm": 38.662139892578125,
      "learning_rate": 2.4710794271727415e-05,
      "loss": 2.7824,
      "step": 450
    },
    {
      "epoch": 0.9766684753119913,
      "eval_loss": 0.6706861853599548,
      "eval_runtime": 53.787,
      "eval_samples_per_second": 14.446,
      "eval_steps_per_second": 1.822,
      "step": 450
    },
    {
      "epoch": 0.9983722192078134,
      "grad_norm": 25.043182373046875,
      "learning_rate": 2.446083767528193e-05,
      "loss": 2.7357,
      "step": 460
    },
    {
      "epoch": 1.0200759631036354,
      "grad_norm": 15.549626350402832,
      "learning_rate": 2.4206440124138064e-05,
      "loss": 2.7512,
      "step": 470
    },
    {
      "epoch": 1.0417797069994574,
      "grad_norm": 18.95859146118164,
      "learning_rate": 2.3947721033514517e-05,
      "loss": 2.3525,
      "step": 480
    },
    {
      "epoch": 1.0634834508952795,
      "grad_norm": 18.817302703857422,
      "learning_rate": 2.3684801847177732e-05,
      "loss": 2.2039,
      "step": 490
    },
    {
      "epoch": 1.0851871947911014,
      "grad_norm": 23.182357788085938,
      "learning_rate": 2.341780598043574e-05,
      "loss": 2.0556,
      "step": 500
    },
    {
      "epoch": 1.1068909386869235,
      "grad_norm": 34.256813049316406,
      "learning_rate": 2.3146858762206493e-05,
      "loss": 2.2184,
      "step": 510
    },
    {
      "epoch": 1.1285946825827455,
      "grad_norm": 18.3436336517334,
      "learning_rate": 2.287208737618801e-05,
      "loss": 2.5032,
      "step": 520
    },
    {
      "epoch": 1.1502984264785676,
      "grad_norm": 18.193883895874023,
      "learning_rate": 2.259362080115781e-05,
      "loss": 2.1954,
      "step": 530
    },
    {
      "epoch": 1.1720021703743897,
      "grad_norm": 22.53719711303711,
      "learning_rate": 2.231158975042979e-05,
      "loss": 2.2031,
      "step": 540
    },
    {
      "epoch": 1.1937059142702116,
      "grad_norm": 21.267290115356445,
      "learning_rate": 2.2026126610496852e-05,
      "loss": 1.8531,
      "step": 550
    },
    {
      "epoch": 1.2154096581660336,
      "grad_norm": 29.71878433227539,
      "learning_rate": 2.173736537888819e-05,
      "loss": 1.9597,
      "step": 560
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 18.650861740112305,
      "learning_rate": 2.1445441601270276e-05,
      "loss": 2.6653,
      "step": 570
    },
    {
      "epoch": 1.2588171459576776,
      "grad_norm": 22.564220428466797,
      "learning_rate": 2.115049230782124e-05,
      "loss": 2.34,
      "step": 580
    },
    {
      "epoch": 1.2805208898534997,
      "grad_norm": 22.589075088500977,
      "learning_rate": 2.085265594890832e-05,
      "loss": 2.181,
      "step": 590
    },
    {
      "epoch": 1.3022246337493217,
      "grad_norm": 22.656047821044922,
      "learning_rate": 2.055207233009872e-05,
      "loss": 1.9121,
      "step": 600
    },
    {
      "epoch": 1.3022246337493217,
      "eval_loss": 0.6503757834434509,
      "eval_runtime": 53.7768,
      "eval_samples_per_second": 14.449,
      "eval_steps_per_second": 1.822,
      "step": 600
    },
    {
      "epoch": 1.3239283776451438,
      "grad_norm": 33.046363830566406,
      "learning_rate": 2.0248882546534327e-05,
      "loss": 1.9914,
      "step": 610
    },
    {
      "epoch": 1.345632121540966,
      "grad_norm": 21.024412155151367,
      "learning_rate": 1.9943228916701108e-05,
      "loss": 2.5415,
      "step": 620
    },
    {
      "epoch": 1.3673358654367878,
      "grad_norm": 20.984058380126953,
      "learning_rate": 1.963525491562421e-05,
      "loss": 2.329,
      "step": 630
    },
    {
      "epoch": 1.3890396093326098,
      "grad_norm": 23.811756134033203,
      "learning_rate": 1.9325105107520264e-05,
      "loss": 2.236,
      "step": 640
    },
    {
      "epoch": 1.410743353228432,
      "grad_norm": 24.431550979614258,
      "learning_rate": 1.9012925077938318e-05,
      "loss": 2.0522,
      "step": 650
    },
    {
      "epoch": 1.432447097124254,
      "grad_norm": 27.39398193359375,
      "learning_rate": 1.8698861365421433e-05,
      "loss": 1.8751,
      "step": 660
    },
    {
      "epoch": 1.454150841020076,
      "grad_norm": 18.39029312133789,
      "learning_rate": 1.8383061392720914e-05,
      "loss": 2.6245,
      "step": 670
    },
    {
      "epoch": 1.475854584915898,
      "grad_norm": 19.114816665649414,
      "learning_rate": 1.8065673397595475e-05,
      "loss": 2.1778,
      "step": 680
    },
    {
      "epoch": 1.49755832881172,
      "grad_norm": 20.83147621154785,
      "learning_rate": 1.7746846363227843e-05,
      "loss": 1.9417,
      "step": 690
    },
    {
      "epoch": 1.519262072707542,
      "grad_norm": 26.67376708984375,
      "learning_rate": 1.7426729948291474e-05,
      "loss": 1.9912,
      "step": 700
    },
    {
      "epoch": 1.540965816603364,
      "grad_norm": 29.251083374023438,
      "learning_rate": 1.7105474416700165e-05,
      "loss": 2.0298,
      "step": 710
    },
    {
      "epoch": 1.5626695604991863,
      "grad_norm": 17.292633056640625,
      "learning_rate": 1.6783230567073597e-05,
      "loss": 2.4696,
      "step": 720
    },
    {
      "epoch": 1.5843733043950081,
      "grad_norm": 20.139678955078125,
      "learning_rate": 1.646014966195185e-05,
      "loss": 2.2227,
      "step": 730
    },
    {
      "epoch": 1.6060770482908302,
      "grad_norm": 20.934541702270508,
      "learning_rate": 1.613638335679216e-05,
      "loss": 1.9018,
      "step": 740
    },
    {
      "epoch": 1.6277807921866523,
      "grad_norm": 24.31667709350586,
      "learning_rate": 1.5812083628781265e-05,
      "loss": 2.1797,
      "step": 750
    },
    {
      "epoch": 1.6277807921866523,
      "eval_loss": 0.647061824798584,
      "eval_runtime": 53.7706,
      "eval_samples_per_second": 14.45,
      "eval_steps_per_second": 1.823,
      "step": 750
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": 36.196144104003906,
      "learning_rate": 1.548740270549671e-05,
      "loss": 2.0389,
      "step": 760
    },
    {
      "epoch": 1.6711882799782962,
      "grad_norm": 20.02777671813965,
      "learning_rate": 1.5162492993450599e-05,
      "loss": 2.4617,
      "step": 770
    },
    {
      "epoch": 1.6928920238741183,
      "grad_norm": 20.28060531616211,
      "learning_rate": 1.4837507006549403e-05,
      "loss": 2.1809,
      "step": 780
    },
    {
      "epoch": 1.7145957677699402,
      "grad_norm": 22.740869522094727,
      "learning_rate": 1.4512597294503295e-05,
      "loss": 2.0388,
      "step": 790
    },
    {
      "epoch": 1.7362995116657625,
      "grad_norm": 23.173282623291016,
      "learning_rate": 1.4187916371218739e-05,
      "loss": 2.0224,
      "step": 800
    },
    {
      "epoch": 1.7580032555615843,
      "grad_norm": 40.70626449584961,
      "learning_rate": 1.3863616643207844e-05,
      "loss": 1.9738,
      "step": 810
    },
    {
      "epoch": 1.7797069994574064,
      "grad_norm": 19.63157844543457,
      "learning_rate": 1.3539850338048156e-05,
      "loss": 2.5696,
      "step": 820
    },
    {
      "epoch": 1.8014107433532285,
      "grad_norm": 21.02994155883789,
      "learning_rate": 1.3216769432926405e-05,
      "loss": 2.2346,
      "step": 830
    },
    {
      "epoch": 1.8231144872490503,
      "grad_norm": 21.89013671875,
      "learning_rate": 1.2894525583299835e-05,
      "loss": 2.0149,
      "step": 840
    },
    {
      "epoch": 1.8448182311448726,
      "grad_norm": 20.857643127441406,
      "learning_rate": 1.2573270051708529e-05,
      "loss": 1.7583,
      "step": 850
    },
    {
      "epoch": 1.8665219750406945,
      "grad_norm": 48.44206237792969,
      "learning_rate": 1.2253153636772158e-05,
      "loss": 2.221,
      "step": 860
    },
    {
      "epoch": 1.8882257189365166,
      "grad_norm": 19.892345428466797,
      "learning_rate": 1.193432660240453e-05,
      "loss": 2.4434,
      "step": 870
    },
    {
      "epoch": 1.9099294628323387,
      "grad_norm": 22.947458267211914,
      "learning_rate": 1.1616938607279089e-05,
      "loss": 2.2474,
      "step": 880
    },
    {
      "epoch": 1.9316332067281605,
      "grad_norm": 21.839048385620117,
      "learning_rate": 1.1301138634578571e-05,
      "loss": 1.947,
      "step": 890
    },
    {
      "epoch": 1.9533369506239826,
      "grad_norm": 33.06451416015625,
      "learning_rate": 1.098707492206169e-05,
      "loss": 2.0453,
      "step": 900
    },
    {
      "epoch": 1.9533369506239826,
      "eval_loss": 0.636073112487793,
      "eval_runtime": 53.9004,
      "eval_samples_per_second": 14.415,
      "eval_steps_per_second": 1.818,
      "step": 900
    },
    {
      "epoch": 1.9750406945198047,
      "grad_norm": 33.91230773925781,
      "learning_rate": 1.067489489247974e-05,
      "loss": 1.9067,
      "step": 910
    },
    {
      "epoch": 1.9967444384156265,
      "grad_norm": 28.854825973510742,
      "learning_rate": 1.036474508437579e-05,
      "loss": 2.3281,
      "step": 920
    },
    {
      "epoch": 2.018448182311449,
      "grad_norm": 18.260103225708008,
      "learning_rate": 1.0056771083298894e-05,
      "loss": 2.1337,
      "step": 930
    },
    {
      "epoch": 2.0401519262072707,
      "grad_norm": 19.979646682739258,
      "learning_rate": 9.751117453465674e-06,
      "loss": 1.6345,
      "step": 940
    },
    {
      "epoch": 2.0618556701030926,
      "grad_norm": 22.703859329223633,
      "learning_rate": 9.447927669901284e-06,
      "loss": 1.634,
      "step": 950
    },
    {
      "epoch": 2.083559413998915,
      "grad_norm": 21.72873878479004,
      "learning_rate": 9.147344051091682e-06,
      "loss": 1.5881,
      "step": 960
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 31.957630157470703,
      "learning_rate": 8.849507692178758e-06,
      "loss": 1.3856,
      "step": 970
    },
    {
      "epoch": 2.126966901790559,
      "grad_norm": 21.75389862060547,
      "learning_rate": 8.554558398729726e-06,
      "loss": 1.9382,
      "step": 980
    },
    {
      "epoch": 2.148670645686381,
      "grad_norm": 23.939027786254883,
      "learning_rate": 8.262634621111819e-06,
      "loss": 1.8201,
      "step": 990
    },
    {
      "epoch": 2.1703743895822027,
      "grad_norm": 21.948673248291016,
      "learning_rate": 7.97387338950315e-06,
      "loss": 1.5186,
      "step": 1000
    },
    {
      "epoch": 2.192078133478025,
      "grad_norm": 26.39198112487793,
      "learning_rate": 7.688410249570214e-06,
      "loss": 1.4693,
      "step": 1010
    },
    {
      "epoch": 2.213781877373847,
      "grad_norm": 43.11570358276367,
      "learning_rate": 7.4063791988421905e-06,
      "loss": 1.3836,
      "step": 1020
    },
    {
      "epoch": 2.235485621269669,
      "grad_norm": 21.80547523498535,
      "learning_rate": 7.127912623811993e-06,
      "loss": 1.9962,
      "step": 1030
    },
    {
      "epoch": 2.257189365165491,
      "grad_norm": 20.71767234802246,
      "learning_rate": 6.853141237793507e-06,
      "loss": 1.6606,
      "step": 1040
    },
    {
      "epoch": 2.278893109061313,
      "grad_norm": 21.81035614013672,
      "learning_rate": 6.582194019564266e-06,
      "loss": 1.4825,
      "step": 1050
    },
    {
      "epoch": 2.278893109061313,
      "eval_loss": 0.6611286997795105,
      "eval_runtime": 53.8731,
      "eval_samples_per_second": 14.423,
      "eval_steps_per_second": 1.819,
      "step": 1050
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4722426201964544e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}