{
  "best_metric": 5.704630374908447,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.04357298474945534,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00043572984749455336,
      "grad_norm": 6.661526679992676,
      "learning_rate": 5e-06,
      "loss": 4.1538,
      "step": 1
    },
    {
      "epoch": 0.00043572984749455336,
      "eval_loss": 8.217473030090332,
      "eval_runtime": 340.1891,
      "eval_samples_per_second": 11.364,
      "eval_steps_per_second": 5.682,
      "step": 1
    },
    {
      "epoch": 0.0008714596949891067,
      "grad_norm": 10.892069816589355,
      "learning_rate": 1e-05,
      "loss": 6.0324,
      "step": 2
    },
    {
      "epoch": 0.00130718954248366,
      "grad_norm": 10.684877395629883,
      "learning_rate": 1.5e-05,
      "loss": 6.2791,
      "step": 3
    },
    {
      "epoch": 0.0017429193899782135,
      "grad_norm": 8.87505054473877,
      "learning_rate": 2e-05,
      "loss": 6.2904,
      "step": 4
    },
    {
      "epoch": 0.002178649237472767,
      "grad_norm": 8.179178237915039,
      "learning_rate": 2.5e-05,
      "loss": 6.3373,
      "step": 5
    },
    {
      "epoch": 0.00261437908496732,
      "grad_norm": 7.012093544006348,
      "learning_rate": 3e-05,
      "loss": 6.1102,
      "step": 6
    },
    {
      "epoch": 0.0030501089324618735,
      "grad_norm": 5.900923728942871,
      "learning_rate": 3.5e-05,
      "loss": 6.0426,
      "step": 7
    },
    {
      "epoch": 0.003485838779956427,
      "grad_norm": 5.232330322265625,
      "learning_rate": 4e-05,
      "loss": 5.8226,
      "step": 8
    },
    {
      "epoch": 0.00392156862745098,
      "grad_norm": 5.2970099449157715,
      "learning_rate": 4.5e-05,
      "loss": 5.7611,
      "step": 9
    },
    {
      "epoch": 0.004357298474945534,
      "grad_norm": 4.734566688537598,
      "learning_rate": 5e-05,
      "loss": 5.5745,
      "step": 10
    },
    {
      "epoch": 0.004793028322440087,
      "grad_norm": 5.093973159790039,
      "learning_rate": 5.500000000000001e-05,
      "loss": 5.3122,
      "step": 11
    },
    {
      "epoch": 0.00522875816993464,
      "grad_norm": 5.139525890350342,
      "learning_rate": 6e-05,
      "loss": 4.7725,
      "step": 12
    },
    {
      "epoch": 0.005664488017429194,
      "grad_norm": 5.895652770996094,
      "learning_rate": 6.500000000000001e-05,
      "loss": 4.8962,
      "step": 13
    },
    {
      "epoch": 0.006100217864923747,
      "grad_norm": 6.588743686676025,
      "learning_rate": 7e-05,
      "loss": 4.6153,
      "step": 14
    },
    {
      "epoch": 0.006535947712418301,
      "grad_norm": 6.610407829284668,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.5844,
      "step": 15
    },
    {
      "epoch": 0.006971677559912854,
      "grad_norm": 6.700985431671143,
      "learning_rate": 8e-05,
      "loss": 4.6403,
      "step": 16
    },
    {
      "epoch": 0.007407407407407408,
      "grad_norm": 10.431180953979492,
      "learning_rate": 8.5e-05,
      "loss": 4.938,
      "step": 17
    },
    {
      "epoch": 0.00784313725490196,
      "grad_norm": 8.540962219238281,
      "learning_rate": 9e-05,
      "loss": 4.2487,
      "step": 18
    },
    {
      "epoch": 0.008278867102396514,
      "grad_norm": 6.343726634979248,
      "learning_rate": 9.5e-05,
      "loss": 3.9906,
      "step": 19
    },
    {
      "epoch": 0.008714596949891068,
      "grad_norm": 8.328210830688477,
      "learning_rate": 0.0001,
      "loss": 3.6193,
      "step": 20
    },
    {
      "epoch": 0.009150326797385621,
      "grad_norm": 8.390244483947754,
      "learning_rate": 9.999238475781957e-05,
      "loss": 4.4845,
      "step": 21
    },
    {
      "epoch": 0.009586056644880174,
      "grad_norm": 10.12529468536377,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.4296,
      "step": 22
    },
    {
      "epoch": 0.010021786492374727,
      "grad_norm": 9.76449966430664,
      "learning_rate": 9.99314767377287e-05,
      "loss": 4.2863,
      "step": 23
    },
    {
      "epoch": 0.01045751633986928,
      "grad_norm": 9.467538833618164,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.4368,
      "step": 24
    },
    {
      "epoch": 0.010893246187363835,
      "grad_norm": 10.188558578491211,
      "learning_rate": 9.980973490458728e-05,
      "loss": 4.4229,
      "step": 25
    },
    {
      "epoch": 0.011328976034858388,
      "grad_norm": 11.059619903564453,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.7331,
      "step": 26
    },
    {
      "epoch": 0.011764705882352941,
      "grad_norm": 10.435291290283203,
      "learning_rate": 9.962730758206611e-05,
      "loss": 4.2074,
      "step": 27
    },
    {
      "epoch": 0.012200435729847494,
      "grad_norm": 9.469438552856445,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.114,
      "step": 28
    },
    {
      "epoch": 0.012636165577342049,
      "grad_norm": 9.631402969360352,
      "learning_rate": 9.938441702975689e-05,
      "loss": 4.1015,
      "step": 29
    },
    {
      "epoch": 0.013071895424836602,
      "grad_norm": 8.966801643371582,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.0241,
      "step": 30
    },
    {
      "epoch": 0.013507625272331155,
      "grad_norm": 9.54156494140625,
      "learning_rate": 9.908135917238321e-05,
      "loss": 3.788,
      "step": 31
    },
    {
      "epoch": 0.013943355119825708,
      "grad_norm": 10.83459758758545,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.7602,
      "step": 32
    },
    {
      "epoch": 0.01437908496732026,
      "grad_norm": 10.709683418273926,
      "learning_rate": 9.871850323926177e-05,
      "loss": 3.734,
      "step": 33
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 7.097393989562988,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.3935,
      "step": 34
    },
    {
      "epoch": 0.015250544662309368,
      "grad_norm": 8.187254905700684,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.2138,
      "step": 35
    },
    {
      "epoch": 0.01568627450980392,
      "grad_norm": 9.31251049041748,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.8108,
      "step": 36
    },
    {
      "epoch": 0.016122004357298474,
      "grad_norm": 21.035181045532227,
      "learning_rate": 9.781523779815179e-05,
      "loss": 3.7908,
      "step": 37
    },
    {
      "epoch": 0.016557734204793027,
      "grad_norm": 13.045050621032715,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.597,
      "step": 38
    },
    {
      "epoch": 0.01699346405228758,
      "grad_norm": 12.55672836303711,
      "learning_rate": 9.727592877996585e-05,
      "loss": 3.7547,
      "step": 39
    },
    {
      "epoch": 0.017429193899782137,
      "grad_norm": 12.06466007232666,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.5667,
      "step": 40
    },
    {
      "epoch": 0.01786492374727669,
      "grad_norm": 8.983872413635254,
      "learning_rate": 9.667902132486009e-05,
      "loss": 3.4935,
      "step": 41
    },
    {
      "epoch": 0.018300653594771243,
      "grad_norm": 13.591109275817871,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.7854,
      "step": 42
    },
    {
      "epoch": 0.018736383442265796,
      "grad_norm": 10.855591773986816,
      "learning_rate": 9.602524267262203e-05,
      "loss": 3.5952,
      "step": 43
    },
    {
      "epoch": 0.01917211328976035,
      "grad_norm": 9.983095169067383,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.4844,
      "step": 44
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 11.39333724975586,
      "learning_rate": 9.53153893518325e-05,
      "loss": 3.4564,
      "step": 45
    },
    {
      "epoch": 0.020043572984749455,
      "grad_norm": 20.231857299804688,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.0669,
      "step": 46
    },
    {
      "epoch": 0.020479302832244008,
      "grad_norm": 19.679521560668945,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.4897,
      "step": 47
    },
    {
      "epoch": 0.02091503267973856,
      "grad_norm": 14.81116008758545,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.3553,
      "step": 48
    },
    {
      "epoch": 0.021350762527233117,
      "grad_norm": 13.380983352661133,
      "learning_rate": 9.373098535696979e-05,
      "loss": 4.7489,
      "step": 49
    },
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 27.759239196777344,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.8204,
      "step": 50
    },
    {
      "epoch": 0.02178649237472767,
      "eval_loss": 6.364690780639648,
      "eval_runtime": 341.999,
      "eval_samples_per_second": 11.304,
      "eval_steps_per_second": 5.652,
      "step": 50
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 32.31818771362305,
      "learning_rate": 9.285836503510562e-05,
      "loss": 4.8942,
      "step": 51
    },
    {
      "epoch": 0.022657952069716776,
      "grad_norm": 8.852598190307617,
      "learning_rate": 9.24024048078213e-05,
      "loss": 5.1201,
      "step": 52
    },
    {
      "epoch": 0.02309368191721133,
      "grad_norm": 5.560345649719238,
      "learning_rate": 9.193352839727121e-05,
      "loss": 4.7122,
      "step": 53
    },
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 5.5676703453063965,
      "learning_rate": 9.145187862775209e-05,
      "loss": 4.4284,
      "step": 54
    },
    {
      "epoch": 0.023965141612200435,
      "grad_norm": 3.9773125648498535,
      "learning_rate": 9.09576022144496e-05,
      "loss": 4.2563,
      "step": 55
    },
    {
      "epoch": 0.024400871459694988,
      "grad_norm": 3.3628735542297363,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.0718,
      "step": 56
    },
    {
      "epoch": 0.02483660130718954,
      "grad_norm": 3.6923017501831055,
      "learning_rate": 8.993177550236464e-05,
      "loss": 4.1137,
      "step": 57
    },
    {
      "epoch": 0.025272331154684097,
      "grad_norm": 3.8369545936584473,
      "learning_rate": 8.940053768033609e-05,
      "loss": 3.9718,
      "step": 58
    },
    {
      "epoch": 0.02570806100217865,
      "grad_norm": 3.6480236053466797,
      "learning_rate": 8.885729807284856e-05,
      "loss": 3.9776,
      "step": 59
    },
    {
      "epoch": 0.026143790849673203,
      "grad_norm": 4.316795349121094,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.9067,
      "step": 60
    },
    {
      "epoch": 0.026579520697167756,
      "grad_norm": 3.6981241703033447,
      "learning_rate": 8.773547901113862e-05,
      "loss": 3.7386,
      "step": 61
    },
    {
      "epoch": 0.02701525054466231,
      "grad_norm": 3.8812918663024902,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.9539,
      "step": 62
    },
    {
      "epoch": 0.027450980392156862,
      "grad_norm": 4.209654331207275,
      "learning_rate": 8.656768508095853e-05,
      "loss": 3.7761,
      "step": 63
    },
    {
      "epoch": 0.027886710239651415,
      "grad_norm": 4.035881519317627,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.9857,
      "step": 64
    },
    {
      "epoch": 0.02832244008714597,
      "grad_norm": 4.345121383666992,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.6951,
      "step": 65
    },
    {
      "epoch": 0.02875816993464052,
      "grad_norm": 4.360794544219971,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.6316,
      "step": 66
    },
    {
      "epoch": 0.029193899782135078,
      "grad_norm": 5.3004631996154785,
      "learning_rate": 8.409991800312493e-05,
      "loss": 3.4737,
      "step": 67
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 6.006906986236572,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.4292,
      "step": 68
    },
    {
      "epoch": 0.030065359477124184,
      "grad_norm": 5.198672771453857,
      "learning_rate": 8.280295144952536e-05,
      "loss": 2.8169,
      "step": 69
    },
    {
      "epoch": 0.030501089324618737,
      "grad_norm": 5.72125768661499,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.8071,
      "step": 70
    },
    {
      "epoch": 0.03093681917211329,
      "grad_norm": 5.537723064422607,
      "learning_rate": 8.146601955249188e-05,
      "loss": 2.919,
      "step": 71
    },
    {
      "epoch": 0.03137254901960784,
      "grad_norm": 5.822765827178955,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.339,
      "step": 72
    },
    {
      "epoch": 0.0318082788671024,
      "grad_norm": 7.500765800476074,
      "learning_rate": 8.009075115760243e-05,
      "loss": 4.1151,
      "step": 73
    },
    {
      "epoch": 0.03224400871459695,
      "grad_norm": 7.959412574768066,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.0335,
      "step": 74
    },
    {
      "epoch": 0.032679738562091505,
      "grad_norm": 8.24825382232666,
      "learning_rate": 7.86788218175523e-05,
      "loss": 3.7507,
      "step": 75
    },
    {
      "epoch": 0.033115468409586055,
      "grad_norm": 8.649166107177734,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.6593,
      "step": 76
    },
    {
      "epoch": 0.03355119825708061,
      "grad_norm": 9.08403205871582,
      "learning_rate": 7.723195175075136e-05,
      "loss": 3.4322,
      "step": 77
    },
    {
      "epoch": 0.03398692810457516,
      "grad_norm": 7.34392786026001,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.1185,
      "step": 78
    },
    {
      "epoch": 0.03442265795206972,
      "grad_norm": 8.574236869812012,
      "learning_rate": 7.575190374550272e-05,
      "loss": 3.1579,
      "step": 79
    },
    {
      "epoch": 0.034858387799564274,
      "grad_norm": 6.6132073402404785,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.0925,
      "step": 80
    },
    {
      "epoch": 0.03529411764705882,
      "grad_norm": 8.333246231079102,
      "learning_rate": 7.424048101231686e-05,
      "loss": 3.0313,
      "step": 81
    },
    {
      "epoch": 0.03572984749455338,
      "grad_norm": 8.929666519165039,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.2752,
      "step": 82
    },
    {
      "epoch": 0.03616557734204793,
      "grad_norm": 8.084465980529785,
      "learning_rate": 7.269952498697734e-05,
      "loss": 3.1595,
      "step": 83
    },
    {
      "epoch": 0.036601307189542485,
      "grad_norm": 11.703425407409668,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.6573,
      "step": 84
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 8.313312530517578,
      "learning_rate": 7.113091308703498e-05,
      "loss": 2.9834,
      "step": 85
    },
    {
      "epoch": 0.03747276688453159,
      "grad_norm": 10.730279922485352,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.3908,
      "step": 86
    },
    {
      "epoch": 0.03790849673202614,
      "grad_norm": 7.744607925415039,
      "learning_rate": 6.953655642446368e-05,
      "loss": 3.1383,
      "step": 87
    },
    {
      "epoch": 0.0383442265795207,
      "grad_norm": 7.350200653076172,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.2401,
      "step": 88
    },
    {
      "epoch": 0.038779956427015254,
      "grad_norm": 7.381011009216309,
      "learning_rate": 6.7918397477265e-05,
      "loss": 3.009,
      "step": 89
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 8.214192390441895,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.2592,
      "step": 90
    },
    {
      "epoch": 0.03965141612200436,
      "grad_norm": 7.677833080291748,
      "learning_rate": 6.627840772285784e-05,
      "loss": 3.0722,
      "step": 91
    },
    {
      "epoch": 0.04008714596949891,
      "grad_norm": 7.761831760406494,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.3408,
      "step": 92
    },
    {
      "epoch": 0.040522875816993466,
      "grad_norm": 11.57331657409668,
      "learning_rate": 6.461858523613684e-05,
      "loss": 3.6557,
      "step": 93
    },
    {
      "epoch": 0.040958605664488015,
      "grad_norm": 11.86795425415039,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.2901,
      "step": 94
    },
    {
      "epoch": 0.04139433551198257,
      "grad_norm": 7.4138288497924805,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.0572,
      "step": 95
    },
    {
      "epoch": 0.04183006535947712,
      "grad_norm": 9.516829490661621,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.0378,
      "step": 96
    },
    {
      "epoch": 0.04226579520697168,
      "grad_norm": 14.580899238586426,
      "learning_rate": 6.124755271719325e-05,
      "loss": 3.3854,
      "step": 97
    },
    {
      "epoch": 0.042701525054466234,
      "grad_norm": 11.462180137634277,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.1607,
      "step": 98
    },
    {
      "epoch": 0.043137254901960784,
      "grad_norm": 11.856027603149414,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 3.5423,
      "step": 99
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 15.242999076843262,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.5773,
      "step": 100
    },
    {
      "epoch": 0.04357298474945534,
      "eval_loss": 5.704630374908447,
      "eval_runtime": 342.2942,
      "eval_samples_per_second": 11.294,
      "eval_steps_per_second": 5.647,
      "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4762717692821504e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}