{
  "best_metric": 0.12817183136940002,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.7204301075268817,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017204301075268817,
      "grad_norm": 4.606525897979736,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 1
    },
    {
      "epoch": 0.017204301075268817,
      "eval_loss": 1.4783204793930054,
      "eval_runtime": 5.1427,
      "eval_samples_per_second": 76.225,
      "eval_steps_per_second": 9.528,
      "step": 1
    },
    {
      "epoch": 0.034408602150537634,
      "grad_norm": 7.242240905761719,
      "learning_rate": 4e-05,
      "loss": 0.6626,
      "step": 2
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 8.026199340820312,
      "learning_rate": 6e-05,
      "loss": 0.688,
      "step": 3
    },
    {
      "epoch": 0.06881720430107527,
      "grad_norm": 4.369725227355957,
      "learning_rate": 8e-05,
      "loss": 0.3961,
      "step": 4
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 3.2137558460235596,
      "learning_rate": 0.0001,
      "loss": 0.3013,
      "step": 5
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 1.875462532043457,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2243,
      "step": 6
    },
    {
      "epoch": 0.12043010752688173,
      "grad_norm": 1.5983223915100098,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2217,
      "step": 7
    },
    {
      "epoch": 0.13763440860215054,
      "grad_norm": 0.936194121837616,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1533,
      "step": 8
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 0.9381992816925049,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.175,
      "step": 9
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.8003645539283752,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1827,
      "step": 10
    },
    {
      "epoch": 0.18924731182795698,
      "grad_norm": 0.9426307082176208,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2171,
      "step": 11
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 0.8257225155830383,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2083,
      "step": 12
    },
    {
      "epoch": 0.22365591397849463,
      "grad_norm": 0.34718796610832214,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0771,
      "step": 13
    },
    {
      "epoch": 0.24086021505376345,
      "grad_norm": 0.42136135697364807,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0706,
      "step": 14
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.37979984283447266,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0864,
      "step": 15
    },
    {
      "epoch": 0.2752688172043011,
      "grad_norm": 0.5699045062065125,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1064,
      "step": 16
    },
    {
      "epoch": 0.2924731182795699,
      "grad_norm": 0.459989458322525,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0981,
      "step": 17
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 0.4138818085193634,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1106,
      "step": 18
    },
    {
      "epoch": 0.32688172043010755,
      "grad_norm": 0.4874074459075928,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1131,
      "step": 19
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.5561056733131409,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1247,
      "step": 20
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 0.5631709098815918,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1304,
      "step": 21
    },
    {
      "epoch": 0.37849462365591396,
      "grad_norm": 0.5898393392562866,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1443,
      "step": 22
    },
    {
      "epoch": 0.3956989247311828,
      "grad_norm": 0.5762998461723328,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1351,
      "step": 23
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 0.7826749682426453,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1765,
      "step": 24
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.8732266426086426,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2271,
      "step": 25
    },
    {
      "epoch": 0.43010752688172044,
      "eval_loss": 0.1378888338804245,
      "eval_runtime": 5.1517,
      "eval_samples_per_second": 76.091,
      "eval_steps_per_second": 9.511,
      "step": 25
    },
    {
      "epoch": 0.44731182795698926,
      "grad_norm": 0.16348931193351746,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0444,
      "step": 26
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 0.2577475905418396,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0661,
      "step": 27
    },
    {
      "epoch": 0.4817204301075269,
      "grad_norm": 0.3649281859397888,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0907,
      "step": 28
    },
    {
      "epoch": 0.4989247311827957,
      "grad_norm": 0.3533531427383423,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0912,
      "step": 29
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.33457306027412415,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0926,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.4363839030265808,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1043,
      "step": 31
    },
    {
      "epoch": 0.5505376344086022,
      "grad_norm": 0.4272841513156891,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.108,
      "step": 32
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 0.4825282096862793,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1199,
      "step": 33
    },
    {
      "epoch": 0.5849462365591398,
      "grad_norm": 0.48275941610336304,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1211,
      "step": 34
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.528899073600769,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.142,
      "step": 35
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 0.5261264443397522,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1601,
      "step": 36
    },
    {
      "epoch": 0.6365591397849463,
      "grad_norm": 0.7465059757232666,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1977,
      "step": 37
    },
    {
      "epoch": 0.6537634408602151,
      "grad_norm": 0.2546450197696686,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0638,
      "step": 38
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 0.20276089012622833,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0537,
      "step": 39
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 0.25185713171958923,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0687,
      "step": 40
    },
    {
      "epoch": 0.7053763440860215,
      "grad_norm": 0.2671894431114197,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0798,
      "step": 41
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 0.2557334899902344,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.082,
      "step": 42
    },
    {
      "epoch": 0.7397849462365591,
      "grad_norm": 0.3387112021446228,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.094,
      "step": 43
    },
    {
      "epoch": 0.7569892473118279,
      "grad_norm": 0.3676891624927521,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1054,
      "step": 44
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.38841351866722107,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1109,
      "step": 45
    },
    {
      "epoch": 0.7913978494623656,
      "grad_norm": 0.4301333725452423,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1176,
      "step": 46
    },
    {
      "epoch": 0.8086021505376344,
      "grad_norm": 0.5915757417678833,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1329,
      "step": 47
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 0.47758930921554565,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1547,
      "step": 48
    },
    {
      "epoch": 0.843010752688172,
      "grad_norm": 0.6082626581192017,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.1622,
      "step": 49
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.9094322323799133,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2415,
      "step": 50
    },
    {
      "epoch": 0.8602150537634409,
      "eval_loss": 0.1337614506483078,
      "eval_runtime": 5.1509,
      "eval_samples_per_second": 76.103,
      "eval_steps_per_second": 9.513,
      "step": 50
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 0.16892726719379425,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0471,
      "step": 51
    },
    {
      "epoch": 0.8946236559139785,
      "grad_norm": 0.22629976272583008,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.071,
      "step": 52
    },
    {
      "epoch": 0.9118279569892473,
      "grad_norm": 0.27249693870544434,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.088,
      "step": 53
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 0.348569393157959,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0997,
      "step": 54
    },
    {
      "epoch": 0.946236559139785,
      "grad_norm": 0.39192450046539307,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1093,
      "step": 55
    },
    {
      "epoch": 0.9634408602150538,
      "grad_norm": 0.4284210503101349,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.125,
      "step": 56
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 0.46482330560684204,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1557,
      "step": 57
    },
    {
      "epoch": 0.9978494623655914,
      "grad_norm": 0.6542206406593323,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1886,
      "step": 58
    },
    {
      "epoch": 1.0150537634408603,
      "grad_norm": 1.1102313995361328,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1144,
      "step": 59
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.18279777467250824,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0531,
      "step": 60
    },
    {
      "epoch": 1.049462365591398,
      "grad_norm": 0.22511711716651917,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0629,
      "step": 61
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.22818058729171753,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0709,
      "step": 62
    },
    {
      "epoch": 1.0838709677419356,
      "grad_norm": 0.260358065366745,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0737,
      "step": 63
    },
    {
      "epoch": 1.1010752688172043,
      "grad_norm": 0.26677557826042175,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0721,
      "step": 64
    },
    {
      "epoch": 1.118279569892473,
      "grad_norm": 0.33065950870513916,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0793,
      "step": 65
    },
    {
      "epoch": 1.135483870967742,
      "grad_norm": 0.3226628303527832,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0804,
      "step": 66
    },
    {
      "epoch": 1.1526881720430107,
      "grad_norm": 0.32454806566238403,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.089,
      "step": 67
    },
    {
      "epoch": 1.1698924731182796,
      "grad_norm": 0.4000396728515625,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1111,
      "step": 68
    },
    {
      "epoch": 1.1870967741935483,
      "grad_norm": 0.3827371299266815,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1163,
      "step": 69
    },
    {
      "epoch": 1.2043010752688172,
      "grad_norm": 0.44900575280189514,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1188,
      "step": 70
    },
    {
      "epoch": 1.221505376344086,
      "grad_norm": 0.2359217256307602,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0565,
      "step": 71
    },
    {
      "epoch": 1.238709677419355,
      "grad_norm": 0.16581252217292786,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0467,
      "step": 72
    },
    {
      "epoch": 1.2559139784946236,
      "grad_norm": 0.20770955085754395,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0592,
      "step": 73
    },
    {
      "epoch": 1.2731182795698925,
      "grad_norm": 0.29444006085395813,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0672,
      "step": 74
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.23994208872318268,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0669,
      "step": 75
    },
    {
      "epoch": 1.2903225806451613,
      "eval_loss": 0.12850216031074524,
      "eval_runtime": 5.1484,
      "eval_samples_per_second": 76.141,
      "eval_steps_per_second": 9.518,
      "step": 75
    },
    {
      "epoch": 1.3075268817204302,
      "grad_norm": 0.2874716520309448,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0689,
      "step": 76
    },
    {
      "epoch": 1.324731182795699,
      "grad_norm": 0.30706581473350525,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0814,
      "step": 77
    },
    {
      "epoch": 1.3419354838709676,
      "grad_norm": 0.3000510334968567,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0781,
      "step": 78
    },
    {
      "epoch": 1.3591397849462366,
      "grad_norm": 0.32307958602905273,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0851,
      "step": 79
    },
    {
      "epoch": 1.3763440860215055,
      "grad_norm": 0.3091932237148285,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0877,
      "step": 80
    },
    {
      "epoch": 1.3935483870967742,
      "grad_norm": 0.34371423721313477,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0888,
      "step": 81
    },
    {
      "epoch": 1.410752688172043,
      "grad_norm": 0.43044352531433105,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1098,
      "step": 82
    },
    {
      "epoch": 1.4279569892473118,
      "grad_norm": 0.5552714467048645,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1314,
      "step": 83
    },
    {
      "epoch": 1.4451612903225808,
      "grad_norm": 0.25689980387687683,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0478,
      "step": 84
    },
    {
      "epoch": 1.4623655913978495,
      "grad_norm": 0.20479311048984528,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0516,
      "step": 85
    },
    {
      "epoch": 1.4795698924731182,
      "grad_norm": 0.24516907334327698,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0633,
      "step": 86
    },
    {
      "epoch": 1.4967741935483871,
      "grad_norm": 0.2650855481624603,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0687,
      "step": 87
    },
    {
      "epoch": 1.513978494623656,
      "grad_norm": 0.2651553452014923,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0724,
      "step": 88
    },
    {
      "epoch": 1.5311827956989248,
      "grad_norm": 0.29894760251045227,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0772,
      "step": 89
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.34153154492378235,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0857,
      "step": 90
    },
    {
      "epoch": 1.5655913978494622,
      "grad_norm": 0.3278230130672455,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0798,
      "step": 91
    },
    {
      "epoch": 1.5827956989247312,
      "grad_norm": 0.35071855783462524,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0855,
      "step": 92
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3552560806274414,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0953,
      "step": 93
    },
    {
      "epoch": 1.6172043010752688,
      "grad_norm": 0.45054829120635986,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1064,
      "step": 94
    },
    {
      "epoch": 1.6344086021505375,
      "grad_norm": 0.4754152297973633,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1122,
      "step": 95
    },
    {
      "epoch": 1.6516129032258065,
      "grad_norm": 0.22052673995494843,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0487,
      "step": 96
    },
    {
      "epoch": 1.6688172043010754,
      "grad_norm": 0.16441720724105835,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0431,
      "step": 97
    },
    {
      "epoch": 1.686021505376344,
      "grad_norm": 0.21347033977508545,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0517,
      "step": 98
    },
    {
      "epoch": 1.7032258064516128,
      "grad_norm": 0.25747179985046387,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0694,
      "step": 99
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.3165276050567627,
      "learning_rate": 0.0,
      "loss": 0.079,
      "step": 100
    },
    {
      "epoch": 1.7204301075268817,
      "eval_loss": 0.12817183136940002,
      "eval_runtime": 5.1471,
      "eval_samples_per_second": 76.159,
      "eval_steps_per_second": 9.52,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.178927560327168e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}