{
  "best_metric": 3.0250446796417236,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.05387931034482758,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005387931034482759,
      "grad_norm": 0.7922934889793396,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.2943,
      "step": 1
    },
    {
      "epoch": 0.0005387931034482759,
      "eval_loss": 3.5711169242858887,
      "eval_runtime": 411.9397,
      "eval_samples_per_second": 7.588,
      "eval_steps_per_second": 3.794,
      "step": 1
    },
    {
      "epoch": 0.0010775862068965517,
      "grad_norm": 0.8404221534729004,
      "learning_rate": 6.666666666666667e-06,
      "loss": 3.3738,
      "step": 2
    },
    {
      "epoch": 0.0016163793103448276,
      "grad_norm": 0.8657654523849487,
      "learning_rate": 1e-05,
      "loss": 3.3441,
      "step": 3
    },
    {
      "epoch": 0.0021551724137931034,
      "grad_norm": 0.8414548635482788,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.4101,
      "step": 4
    },
    {
      "epoch": 0.0026939655172413795,
      "grad_norm": 0.8666375875473022,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.4358,
      "step": 5
    },
    {
      "epoch": 0.003232758620689655,
      "grad_norm": 0.8541607856750488,
      "learning_rate": 2e-05,
      "loss": 3.3805,
      "step": 6
    },
    {
      "epoch": 0.003771551724137931,
      "grad_norm": 0.8899615406990051,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 3.4211,
      "step": 7
    },
    {
      "epoch": 0.004310344827586207,
      "grad_norm": 0.801926851272583,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 3.3736,
      "step": 8
    },
    {
      "epoch": 0.004849137931034483,
      "grad_norm": 0.8513683676719666,
      "learning_rate": 3e-05,
      "loss": 3.41,
      "step": 9
    },
    {
      "epoch": 0.005387931034482759,
      "grad_norm": 0.80379718542099,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.2838,
      "step": 10
    },
    {
      "epoch": 0.005926724137931034,
      "grad_norm": 0.5176191926002502,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 3.2512,
      "step": 11
    },
    {
      "epoch": 0.00646551724137931,
      "grad_norm": 1.1420265436172485,
      "learning_rate": 4e-05,
      "loss": 3.2356,
      "step": 12
    },
    {
      "epoch": 0.007004310344827586,
      "grad_norm": 0.5149586200714111,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 3.277,
      "step": 13
    },
    {
      "epoch": 0.007543103448275862,
      "grad_norm": 0.7136310338973999,
      "learning_rate": 4.666666666666667e-05,
      "loss": 3.2422,
      "step": 14
    },
    {
      "epoch": 0.008081896551724138,
      "grad_norm": 0.6616995930671692,
      "learning_rate": 5e-05,
      "loss": 3.2174,
      "step": 15
    },
    {
      "epoch": 0.008620689655172414,
      "grad_norm": 1.0672518014907837,
      "learning_rate": 5.333333333333333e-05,
      "loss": 3.193,
      "step": 16
    },
    {
      "epoch": 0.009159482758620689,
      "grad_norm": 0.29977813363075256,
      "learning_rate": 5.666666666666667e-05,
      "loss": 3.1336,
      "step": 17
    },
    {
      "epoch": 0.009698275862068966,
      "grad_norm": 0.8956311345100403,
      "learning_rate": 6e-05,
      "loss": 3.1273,
      "step": 18
    },
    {
      "epoch": 0.010237068965517241,
      "grad_norm": 0.3414318561553955,
      "learning_rate": 6.333333333333333e-05,
      "loss": 3.1157,
      "step": 19
    },
    {
      "epoch": 0.010775862068965518,
      "grad_norm": 0.47326546907424927,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.1407,
      "step": 20
    },
    {
      "epoch": 0.011314655172413793,
      "grad_norm": 0.29255905747413635,
      "learning_rate": 7e-05,
      "loss": 3.1171,
      "step": 21
    },
    {
      "epoch": 0.011853448275862068,
      "grad_norm": 0.25283244252204895,
      "learning_rate": 7.333333333333333e-05,
      "loss": 3.0987,
      "step": 22
    },
    {
      "epoch": 0.012392241379310345,
      "grad_norm": 0.6788113713264465,
      "learning_rate": 7.666666666666667e-05,
      "loss": 3.0829,
      "step": 23
    },
    {
      "epoch": 0.01293103448275862,
      "grad_norm": 2.8709752559661865,
      "learning_rate": 8e-05,
      "loss": 3.0979,
      "step": 24
    },
    {
      "epoch": 0.013469827586206896,
      "grad_norm": 0.3539103865623474,
      "learning_rate": 8.333333333333334e-05,
      "loss": 3.0696,
      "step": 25
    },
    {
      "epoch": 0.014008620689655173,
      "grad_norm": 1.9766085147857666,
      "learning_rate": 8.666666666666667e-05,
      "loss": 3.1419,
      "step": 26
    },
    {
      "epoch": 0.014547413793103448,
      "grad_norm": 1.2451584339141846,
      "learning_rate": 9e-05,
      "loss": 3.1152,
      "step": 27
    },
    {
      "epoch": 0.015086206896551725,
      "grad_norm": 3.3829805850982666,
      "learning_rate": 9.333333333333334e-05,
      "loss": 3.1891,
      "step": 28
    },
    {
      "epoch": 0.015625,
      "grad_norm": 2.928429365158081,
      "learning_rate": 9.666666666666667e-05,
      "loss": 3.1886,
      "step": 29
    },
    {
      "epoch": 0.016163793103448277,
      "grad_norm": 1.225688099861145,
      "learning_rate": 0.0001,
      "loss": 3.0961,
      "step": 30
    },
    {
      "epoch": 0.01670258620689655,
      "grad_norm": 1.955092430114746,
      "learning_rate": 9.994965332706573e-05,
      "loss": 3.1565,
      "step": 31
    },
    {
      "epoch": 0.017241379310344827,
      "grad_norm": 1.2886714935302734,
      "learning_rate": 9.979871469976196e-05,
      "loss": 3.2317,
      "step": 32
    },
    {
      "epoch": 0.017780172413793104,
      "grad_norm": 1.1216020584106445,
      "learning_rate": 9.954748808839674e-05,
      "loss": 3.1817,
      "step": 33
    },
    {
      "epoch": 0.018318965517241378,
      "grad_norm": 0.5160207152366638,
      "learning_rate": 9.919647942993148e-05,
      "loss": 3.1562,
      "step": 34
    },
    {
      "epoch": 0.018857758620689655,
      "grad_norm": 0.7734323740005493,
      "learning_rate": 9.874639560909117e-05,
      "loss": 3.1657,
      "step": 35
    },
    {
      "epoch": 0.01939655172413793,
      "grad_norm": 0.583284854888916,
      "learning_rate": 9.819814303479267e-05,
      "loss": 3.2008,
      "step": 36
    },
    {
      "epoch": 0.01993534482758621,
      "grad_norm": 0.2643071115016937,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1859,
      "step": 37
    },
    {
      "epoch": 0.020474137931034482,
      "grad_norm": 0.694346010684967,
      "learning_rate": 9.681174353198687e-05,
      "loss": 3.2295,
      "step": 38
    },
    {
      "epoch": 0.02101293103448276,
      "grad_norm": 0.5720380544662476,
      "learning_rate": 9.597638862757255e-05,
      "loss": 3.2481,
      "step": 39
    },
    {
      "epoch": 0.021551724137931036,
      "grad_norm": 0.3155198395252228,
      "learning_rate": 9.504844339512095e-05,
      "loss": 3.2689,
      "step": 40
    },
    {
      "epoch": 0.02209051724137931,
      "grad_norm": 0.9720726013183594,
      "learning_rate": 9.40297765928369e-05,
      "loss": 3.225,
      "step": 41
    },
    {
      "epoch": 0.022629310344827586,
      "grad_norm": 1.3867518901824951,
      "learning_rate": 9.292243968009331e-05,
      "loss": 3.0532,
      "step": 42
    },
    {
      "epoch": 0.023168103448275863,
      "grad_norm": 1.3067538738250732,
      "learning_rate": 9.172866268606513e-05,
      "loss": 3.0021,
      "step": 43
    },
    {
      "epoch": 0.023706896551724137,
      "grad_norm": 1.5030200481414795,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.0634,
      "step": 44
    },
    {
      "epoch": 0.024245689655172414,
      "grad_norm": 0.237008199095726,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.9759,
      "step": 45
    },
    {
      "epoch": 0.02478448275862069,
      "grad_norm": 0.5865659713745117,
      "learning_rate": 8.765357330018056e-05,
      "loss": 3.0223,
      "step": 46
    },
    {
      "epoch": 0.025323275862068964,
      "grad_norm": 0.6696709394454956,
      "learning_rate": 8.613974319136958e-05,
      "loss": 2.9951,
      "step": 47
    },
    {
      "epoch": 0.02586206896551724,
      "grad_norm": 0.1882406771183014,
      "learning_rate": 8.455313244934324e-05,
      "loss": 3.0037,
      "step": 48
    },
    {
      "epoch": 0.026400862068965518,
      "grad_norm": 0.38517552614212036,
      "learning_rate": 8.289693629698564e-05,
      "loss": 2.9575,
      "step": 49
    },
    {
      "epoch": 0.02693965517241379,
      "grad_norm": 0.9038740992546082,
      "learning_rate": 8.117449009293668e-05,
      "loss": 3.0508,
      "step": 50
    },
    {
      "epoch": 0.02693965517241379,
      "eval_loss": 3.033242702484131,
      "eval_runtime": 414.8921,
      "eval_samples_per_second": 7.534,
      "eval_steps_per_second": 3.767,
      "step": 50
    },
    {
      "epoch": 0.02747844827586207,
      "grad_norm": 1.095533013343811,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.7835,
      "step": 51
    },
    {
      "epoch": 0.028017241379310345,
      "grad_norm": 0.3085789084434509,
      "learning_rate": 7.754484907260513e-05,
      "loss": 2.8091,
      "step": 52
    },
    {
      "epoch": 0.028556034482758622,
      "grad_norm": 0.4151741564273834,
      "learning_rate": 7.564496387029532e-05,
      "loss": 2.8411,
      "step": 53
    },
    {
      "epoch": 0.029094827586206896,
      "grad_norm": 0.284201979637146,
      "learning_rate": 7.369343312364993e-05,
      "loss": 2.8557,
      "step": 54
    },
    {
      "epoch": 0.029633620689655173,
      "grad_norm": 0.30802321434020996,
      "learning_rate": 7.169418695587791e-05,
      "loss": 2.8606,
      "step": 55
    },
    {
      "epoch": 0.03017241379310345,
      "grad_norm": 0.16543473303318024,
      "learning_rate": 6.965125158269619e-05,
      "loss": 2.8668,
      "step": 56
    },
    {
      "epoch": 0.030711206896551723,
      "grad_norm": 0.4956265985965729,
      "learning_rate": 6.756874120406714e-05,
      "loss": 2.9207,
      "step": 57
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.6670874357223511,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.9217,
      "step": 58
    },
    {
      "epoch": 0.03178879310344827,
      "grad_norm": 0.22392654418945312,
      "learning_rate": 6.330184227833376e-05,
      "loss": 2.9207,
      "step": 59
    },
    {
      "epoch": 0.032327586206896554,
      "grad_norm": 0.7628993988037109,
      "learning_rate": 6.112604669781572e-05,
      "loss": 2.9229,
      "step": 60
    },
    {
      "epoch": 0.03286637931034483,
      "grad_norm": 0.5758177042007446,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 2.9308,
      "step": 61
    },
    {
      "epoch": 0.0334051724137931,
      "grad_norm": 0.2536393702030182,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 2.9689,
      "step": 62
    },
    {
      "epoch": 0.03394396551724138,
      "grad_norm": 0.9088274240493774,
      "learning_rate": 5.448196544517168e-05,
      "loss": 2.9812,
      "step": 63
    },
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 0.3271176517009735,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 2.9661,
      "step": 64
    },
    {
      "epoch": 0.03502155172413793,
      "grad_norm": 0.12883682548999786,
      "learning_rate": 5e-05,
      "loss": 2.9647,
      "step": 65
    },
    {
      "epoch": 0.03556034482758621,
      "grad_norm": 0.3966907858848572,
      "learning_rate": 4.775675848247427e-05,
      "loss": 2.9658,
      "step": 66
    },
    {
      "epoch": 0.03609913793103448,
      "grad_norm": 0.37074947357177734,
      "learning_rate": 4.551803455482833e-05,
      "loss": 2.9655,
      "step": 67
    },
    {
      "epoch": 0.036637931034482756,
      "grad_norm": 0.16934780776500702,
      "learning_rate": 4.328833670911724e-05,
      "loss": 3.0221,
      "step": 68
    },
    {
      "epoch": 0.037176724137931036,
      "grad_norm": 0.15378868579864502,
      "learning_rate": 4.107215526006817e-05,
      "loss": 3.0215,
      "step": 69
    },
    {
      "epoch": 0.03771551724137931,
      "grad_norm": 0.23121915757656097,
      "learning_rate": 3.887395330218429e-05,
      "loss": 3.0209,
      "step": 70
    },
    {
      "epoch": 0.03825431034482758,
      "grad_norm": 0.2312898337841034,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 3.0241,
      "step": 71
    },
    {
      "epoch": 0.03879310344827586,
      "grad_norm": 0.13653403520584106,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.0201,
      "step": 72
    },
    {
      "epoch": 0.03933189655172414,
      "grad_norm": 0.18783865869045258,
      "learning_rate": 3.243125879593286e-05,
      "loss": 3.0155,
      "step": 73
    },
    {
      "epoch": 0.03987068965517242,
      "grad_norm": 0.1803734302520752,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 3.0518,
      "step": 74
    },
    {
      "epoch": 0.04040948275862069,
      "grad_norm": 0.171559140086174,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 3.0685,
      "step": 75
    },
    {
      "epoch": 0.040948275862068964,
      "grad_norm": 0.1469101756811142,
      "learning_rate": 2.630656687635007e-05,
      "loss": 3.0742,
      "step": 76
    },
    {
      "epoch": 0.041487068965517244,
      "grad_norm": 0.17329084873199463,
      "learning_rate": 2.43550361297047e-05,
      "loss": 3.0691,
      "step": 77
    },
    {
      "epoch": 0.04202586206896552,
      "grad_norm": 0.26190730929374695,
      "learning_rate": 2.245515092739488e-05,
      "loss": 3.0717,
      "step": 78
    },
    {
      "epoch": 0.04256465517241379,
      "grad_norm": 0.20236724615097046,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.0735,
      "step": 79
    },
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 0.4072014093399048,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 3.0772,
      "step": 80
    },
    {
      "epoch": 0.043642241379310345,
      "grad_norm": 0.22613751888275146,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 3.1248,
      "step": 81
    },
    {
      "epoch": 0.04418103448275862,
      "grad_norm": 0.20124013721942902,
      "learning_rate": 1.544686755065677e-05,
      "loss": 3.1211,
      "step": 82
    },
    {
      "epoch": 0.0447198275862069,
      "grad_norm": 0.3580072820186615,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 3.1244,
      "step": 83
    },
    {
      "epoch": 0.04525862068965517,
      "grad_norm": 0.3929254710674286,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 3.1228,
      "step": 84
    },
    {
      "epoch": 0.045797413793103446,
      "grad_norm": 0.2717115581035614,
      "learning_rate": 1.090842587659851e-05,
      "loss": 3.1604,
      "step": 85
    },
    {
      "epoch": 0.04633620689655173,
      "grad_norm": 0.16544808447360992,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.1741,
      "step": 86
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.23587080836296082,
      "learning_rate": 8.271337313934869e-06,
      "loss": 3.171,
      "step": 87
    },
    {
      "epoch": 0.04741379310344827,
      "grad_norm": 0.281700074672699,
      "learning_rate": 7.077560319906695e-06,
      "loss": 3.2154,
      "step": 88
    },
    {
      "epoch": 0.047952586206896554,
      "grad_norm": 0.46962276101112366,
      "learning_rate": 5.9702234071631e-06,
      "loss": 3.2238,
      "step": 89
    },
    {
      "epoch": 0.04849137931034483,
      "grad_norm": 0.6593974828720093,
      "learning_rate": 4.951556604879048e-06,
      "loss": 3.2778,
      "step": 90
    },
    {
      "epoch": 0.0490301724137931,
      "grad_norm": 0.2813006341457367,
      "learning_rate": 4.023611372427471e-06,
      "loss": 3.1348,
      "step": 91
    },
    {
      "epoch": 0.04956896551724138,
      "grad_norm": 0.2134297639131546,
      "learning_rate": 3.18825646801314e-06,
      "loss": 3.0484,
      "step": 92
    },
    {
      "epoch": 0.050107758620689655,
      "grad_norm": 0.26354482769966125,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.0046,
      "step": 93
    },
    {
      "epoch": 0.05064655172413793,
      "grad_norm": 0.19792447984218597,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 3.0429,
      "step": 94
    },
    {
      "epoch": 0.05118534482758621,
      "grad_norm": 0.21508128941059113,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 3.0099,
      "step": 95
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": 0.23467521369457245,
      "learning_rate": 8.035205700685167e-07,
      "loss": 3.0566,
      "step": 96
    },
    {
      "epoch": 0.052262931034482756,
      "grad_norm": 0.3338031768798828,
      "learning_rate": 4.52511911603265e-07,
      "loss": 3.0219,
      "step": 97
    },
    {
      "epoch": 0.052801724137931036,
      "grad_norm": 0.24319298565387726,
      "learning_rate": 2.012853002380466e-07,
      "loss": 3.0833,
      "step": 98
    },
    {
      "epoch": 0.05334051724137931,
      "grad_norm": 0.28416627645492554,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 3.0058,
      "step": 99
    },
    {
      "epoch": 0.05387931034482758,
      "grad_norm": 0.3014352321624756,
      "learning_rate": 0.0,
      "loss": 3.0246,
      "step": 100
    },
    {
      "epoch": 0.05387931034482758,
      "eval_loss": 3.0250446796417236,
      "eval_runtime": 415.4589,
      "eval_samples_per_second": 7.524,
      "eval_steps_per_second": 3.762,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.4281547880267776e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}