{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03977724741447892,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003977724741447892,
      "grad_norm": 0.0,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0003977724741447892,
      "eval_loss": NaN,
      "eval_runtime": 82.8942,
      "eval_samples_per_second": 12.775,
      "eval_steps_per_second": 1.604,
      "step": 1
    },
    {
      "epoch": 0.0007955449482895784,
      "grad_norm": 0.0,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0011933174224343676,
      "grad_norm": 0.0,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0015910898965791568,
      "grad_norm": 0.0,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.001988862370723946,
      "grad_norm": 0.0,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002386634844868735,
      "grad_norm": 0.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0027844073190135244,
      "grad_norm": 0.0,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0031821797931583136,
      "grad_norm": 0.0,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.003579952267303103,
      "grad_norm": 0.0,
      "learning_rate": 1.5e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.003977724741447892,
      "grad_norm": 0.0,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.004375497215592681,
      "grad_norm": 0.0,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.00477326968973747,
      "grad_norm": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.005171042163882259,
      "grad_norm": 0.0,
      "learning_rate": 2.166666666666667e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.005568814638027049,
      "grad_norm": 0.0,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0059665871121718375,
      "grad_norm": 0.0,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.006364359586316627,
      "grad_norm": 0.0,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.006762132060461416,
      "grad_norm": 0.0,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.007159904534606206,
      "grad_norm": 0.0,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.007557677008750994,
      "grad_norm": 0.0,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.007955449482895784,
      "grad_norm": 0.0,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.008353221957040573,
      "grad_norm": 0.0,
      "learning_rate": 3.5e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.008750994431185362,
      "grad_norm": 0.0,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.009148766905330152,
      "grad_norm": 0.0,
      "learning_rate": 3.833333333333334e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.00954653937947494,
      "grad_norm": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.00994431185361973,
      "grad_norm": 0.0,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.010342084327764518,
      "grad_norm": 0.0,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.010739856801909307,
      "grad_norm": 0.0,
      "learning_rate": 4.5e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.011137629276054098,
      "grad_norm": 0.0,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.011535401750198886,
      "grad_norm": 0.0,
      "learning_rate": 4.833333333333333e-06,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.011933174224343675,
      "grad_norm": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.012330946698488464,
      "grad_norm": 0.0,
      "learning_rate": 4.997482666353287e-06,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.012728719172633254,
      "grad_norm": 0.0,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.013126491646778043,
      "grad_norm": 0.0,
      "learning_rate": 4.977374404419838e-06,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.013524264120922832,
      "grad_norm": 0.0,
      "learning_rate": 4.959823971496575e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.01392203659506762,
      "grad_norm": 0.0,
      "learning_rate": 4.937319780454559e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.014319809069212411,
      "grad_norm": 0.0,
      "learning_rate": 4.909907151739634e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0147175815433572,
      "grad_norm": 0.0,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.015115354017501989,
      "grad_norm": 0.0,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.015513126491646777,
      "grad_norm": 0.0,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.015910898965791568,
      "grad_norm": 0.0,
      "learning_rate": 4.752422169756048e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.016308671439936355,
      "grad_norm": 0.0,
      "learning_rate": 4.701488829641845e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.016706443914081145,
      "grad_norm": 0.0,
      "learning_rate": 4.646121984004666e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.017104216388225936,
      "grad_norm": 0.0,
      "learning_rate": 4.586433134303257e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.017501988862370723,
      "grad_norm": 0.0,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.017899761336515514,
      "grad_norm": 0.0,
      "learning_rate": 4.454578706170075e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.018297533810660304,
      "grad_norm": 0.0,
      "learning_rate": 4.382678665009028e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.01869530628480509,
      "grad_norm": 0.0,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.01909307875894988,
      "grad_norm": 0.0,
      "learning_rate": 4.227656622467162e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.01949085123309467,
      "grad_norm": 0.0,
      "learning_rate": 4.144846814849282e-06,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.01988862370723946,
      "grad_norm": 0.0,
      "learning_rate": 4.058724504646834e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.01988862370723946,
      "eval_loss": NaN,
      "eval_runtime": 83.0868,
      "eval_samples_per_second": 12.746,
      "eval_steps_per_second": 1.601,
      "step": 50
    },
    {
      "epoch": 0.02028639618138425,
      "grad_norm": 0.0,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.020684168655529037,
      "grad_norm": 0.0,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.021081941129673827,
      "grad_norm": 0.0,
      "learning_rate": 3.782248193514766e-06,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.021479713603818614,
      "grad_norm": 0.0,
      "learning_rate": 3.684671656182497e-06,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.021877486077963405,
      "grad_norm": 0.0,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.022275258552108195,
      "grad_norm": 0.0,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.022673031026252982,
      "grad_norm": 0.0,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.023070803500397773,
      "grad_norm": 0.0,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.023468575974542563,
      "grad_norm": 0.0,
      "learning_rate": 3.165092113916688e-06,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.02386634844868735,
      "grad_norm": 0.0,
      "learning_rate": 3.056302334890786e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.02426412092283214,
      "grad_norm": 0.0,
      "learning_rate": 2.946392236996592e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.024661893396976928,
      "grad_norm": 0.0,
      "learning_rate": 2.835583164544139e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.025059665871121718,
      "grad_norm": 0.0,
      "learning_rate": 2.724098272258584e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.02545743834526651,
      "grad_norm": 0.0,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.025855210819411296,
      "grad_norm": 0.0,
      "learning_rate": 2.5e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.026252983293556086,
      "grad_norm": 0.0,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.026650755767700877,
      "grad_norm": 0.0,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.027048528241845664,
      "grad_norm": 0.0,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.027446300715990454,
      "grad_norm": 0.0,
      "learning_rate": 2.053607763003409e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.02784407319013524,
      "grad_norm": 0.0,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.028241845664280032,
      "grad_norm": 0.0,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.028639618138424822,
      "grad_norm": 0.0,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.02903739061256961,
      "grad_norm": 0.0,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.0294351630867144,
      "grad_norm": 0.0,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.029832935560859187,
      "grad_norm": 0.0,
      "learning_rate": 1.415290652206105e-06,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.030230708035003977,
      "grad_norm": 0.0,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.030628480509148768,
      "grad_norm": 0.0,
      "learning_rate": 1.217751806485235e-06,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.031026252983293555,
      "grad_norm": 0.0,
      "learning_rate": 1.122757546369744e-06,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.031424025457438345,
      "grad_norm": 0.0,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.031821797931583136,
      "grad_norm": 0.0,
      "learning_rate": 9.412754953531664e-07,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.032219570405727926,
      "grad_norm": 0.0,
      "learning_rate": 8.551531851507186e-07,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.03261734287987271,
      "grad_norm": 0.0,
      "learning_rate": 7.723433775328385e-07,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.0330151153540175,
      "grad_norm": 0.0,
      "learning_rate": 6.930128404315214e-07,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.03341288782816229,
      "grad_norm": 0.0,
      "learning_rate": 6.17321334990973e-07,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.03381066030230708,
      "grad_norm": 0.0,
      "learning_rate": 5.454212938299256e-07,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.03420843277645187,
      "grad_norm": 0.0,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.034606205250596656,
      "grad_norm": 0.0,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.035003977724741446,
      "grad_norm": 0.0,
      "learning_rate": 3.538780159953348e-07,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.03540175019888624,
      "grad_norm": 0.0,
      "learning_rate": 2.98511170358155e-07,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.03579952267303103,
      "grad_norm": 0.0,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.03619729514717582,
      "grad_norm": 0.0,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.03659506762132061,
      "grad_norm": 0.0,
      "learning_rate": 1.59412823400657e-07,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.03699284009546539,
      "grad_norm": 0.0,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.03739061256961018,
      "grad_norm": 0.0,
      "learning_rate": 9.00928482603669e-08,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.03778838504375497,
      "grad_norm": 0.0,
      "learning_rate": 6.268021954544095e-08,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.03818615751789976,
      "grad_norm": 0.0,
      "learning_rate": 4.017602850342584e-08,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.038583929992044554,
      "grad_norm": 0.0,
      "learning_rate": 2.262559558016325e-08,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.03898170246618934,
      "grad_norm": 0.0,
      "learning_rate": 1.006426501190233e-08,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.03937947494033413,
      "grad_norm": 0.0,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.03977724741447892,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.03977724741447892,
      "eval_loss": NaN,
      "eval_runtime": 83.0715,
      "eval_samples_per_second": 12.748,
      "eval_steps_per_second": 1.601,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.69912849629184e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}