{
  "best_metric": 0.9532889723777771,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 3.0093457943925235,
  "eval_steps": 50,
  "global_step": 161,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 1.7978484630584717,
      "eval_runtime": 1.7929,
      "eval_samples_per_second": 50.198,
      "eval_steps_per_second": 12.828,
      "step": 1
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 7.484181880950928,
      "learning_rate": 3e-05,
      "loss": 7.3462,
      "step": 3
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 5.32301139831543,
      "learning_rate": 6e-05,
      "loss": 7.0775,
      "step": 6
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 4.536668300628662,
      "learning_rate": 9e-05,
      "loss": 6.1639,
      "step": 9
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 4.83793830871582,
      "learning_rate": 9.995672040508655e-05,
      "loss": 5.9664,
      "step": 12
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 4.512387752532959,
      "learning_rate": 9.972970737805311e-05,
      "loss": 5.4463,
      "step": 15
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 3.3357937335968018,
      "learning_rate": 9.930902394260747e-05,
      "loss": 5.397,
      "step": 18
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 2.8627398014068604,
      "learning_rate": 9.86963084340033e-05,
      "loss": 5.2486,
      "step": 21
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 2.5798230171203613,
      "learning_rate": 9.789394704892364e-05,
      "loss": 5.1503,
      "step": 24
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 3.5169315338134766,
      "learning_rate": 9.690506455253073e-05,
      "loss": 5.0864,
      "step": 27
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 2.785013198852539,
      "learning_rate": 9.573351210918974e-05,
      "loss": 4.7364,
      "step": 30
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 2.747760772705078,
      "learning_rate": 9.438385228425938e-05,
      "loss": 4.7173,
      "step": 33
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 2.9312195777893066,
      "learning_rate": 9.286134127535859e-05,
      "loss": 4.5421,
      "step": 36
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 2.8997135162353516,
      "learning_rate": 9.117190844230971e-05,
      "loss": 4.6737,
      "step": 39
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 2.88925838470459,
      "learning_rate": 8.93221332154777e-05,
      "loss": 4.7061,
      "step": 42
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 2.7651543617248535,
      "learning_rate": 8.731921947243469e-05,
      "loss": 4.4704,
      "step": 45
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 2.9074134826660156,
      "learning_rate": 8.517096748273951e-05,
      "loss": 4.566,
      "step": 48
    },
    {
      "epoch": 0.9345794392523364,
      "eval_loss": 1.0549684762954712,
      "eval_runtime": 1.798,
      "eval_samples_per_second": 50.055,
      "eval_steps_per_second": 12.792,
      "step": 50
    },
    {
      "epoch": 0.9532710280373832,
      "grad_norm": 2.6287901401519775,
      "learning_rate": 8.288574353009164e-05,
      "loss": 4.5007,
      "step": 51
    },
    {
      "epoch": 1.0093457943925233,
      "grad_norm": 2.882777214050293,
      "learning_rate": 8.047244733016522e-05,
      "loss": 4.6791,
      "step": 54
    },
    {
      "epoch": 1.0654205607476634,
      "grad_norm": 2.7834925651550293,
      "learning_rate": 7.794047737101297e-05,
      "loss": 4.2182,
      "step": 57
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 2.7983498573303223,
      "learning_rate": 7.529969431102064e-05,
      "loss": 4.0828,
      "step": 60
    },
    {
      "epoch": 1.1775700934579438,
      "grad_norm": 3.095180034637451,
      "learning_rate": 7.256038257695687e-05,
      "loss": 4.0762,
      "step": 63
    },
    {
      "epoch": 1.233644859813084,
      "grad_norm": 3.032648801803589,
      "learning_rate": 6.973321031167383e-05,
      "loss": 4.3798,
      "step": 66
    },
    {
      "epoch": 1.2897196261682242,
      "grad_norm": 3.197693347930908,
      "learning_rate": 6.682918782744032e-05,
      "loss": 4.1759,
      "step": 69
    },
    {
      "epoch": 1.3457943925233644,
      "grad_norm": 3.1764252185821533,
      "learning_rate": 6.385962472670953e-05,
      "loss": 4.1947,
      "step": 72
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 2.944417715072632,
      "learning_rate": 6.083608585731283e-05,
      "loss": 4.1047,
      "step": 75
    },
    {
      "epoch": 1.4579439252336448,
      "grad_norm": 3.2092721462249756,
      "learning_rate": 5.7770346273610254e-05,
      "loss": 4.0432,
      "step": 78
    },
    {
      "epoch": 1.514018691588785,
      "grad_norm": 3.754558801651001,
      "learning_rate": 5.4674345379e-05,
      "loss": 4.2195,
      "step": 81
    },
    {
      "epoch": 1.5700934579439252,
      "grad_norm": 3.33128023147583,
      "learning_rate": 5.1560140428376956e-05,
      "loss": 3.8932,
      "step": 84
    },
    {
      "epoch": 1.6261682242990654,
      "grad_norm": 3.100324869155884,
      "learning_rate": 4.8439859571623035e-05,
      "loss": 4.0706,
      "step": 87
    },
    {
      "epoch": 1.6822429906542056,
      "grad_norm": 3.433746099472046,
      "learning_rate": 4.532565462099999e-05,
      "loss": 3.9536,
      "step": 90
    },
    {
      "epoch": 1.7383177570093458,
      "grad_norm": 3.482595920562744,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 4.1327,
      "step": 93
    },
    {
      "epoch": 1.794392523364486,
      "grad_norm": 3.3688647747039795,
      "learning_rate": 3.9163914142687184e-05,
      "loss": 3.8966,
      "step": 96
    },
    {
      "epoch": 1.8504672897196262,
      "grad_norm": 3.2575838565826416,
      "learning_rate": 3.614037527329048e-05,
      "loss": 3.9248,
      "step": 99
    },
    {
      "epoch": 1.8691588785046729,
      "eval_loss": 0.9720526933670044,
      "eval_runtime": 1.8012,
      "eval_samples_per_second": 49.967,
      "eval_steps_per_second": 12.769,
      "step": 100
    },
    {
      "epoch": 1.9065420560747663,
      "grad_norm": 3.1702170372009277,
      "learning_rate": 3.31708121725597e-05,
      "loss": 3.8573,
      "step": 102
    },
    {
      "epoch": 1.9626168224299065,
      "grad_norm": 3.2316336631774902,
      "learning_rate": 3.0266789688326186e-05,
      "loss": 4.0095,
      "step": 105
    },
    {
      "epoch": 2.0186915887850465,
      "grad_norm": 4.608758449554443,
      "learning_rate": 2.7439617423043145e-05,
      "loss": 4.0982,
      "step": 108
    },
    {
      "epoch": 2.074766355140187,
      "grad_norm": 3.2477152347564697,
      "learning_rate": 2.470030568897938e-05,
      "loss": 3.6945,
      "step": 111
    },
    {
      "epoch": 2.130841121495327,
      "grad_norm": 3.651806116104126,
      "learning_rate": 2.205952262898704e-05,
      "loss": 3.6482,
      "step": 114
    },
    {
      "epoch": 2.1869158878504673,
      "grad_norm": 3.4141387939453125,
      "learning_rate": 1.9527552669834798e-05,
      "loss": 3.6739,
      "step": 117
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 3.712567090988159,
      "learning_rate": 1.711425646990838e-05,
      "loss": 3.9801,
      "step": 120
    },
    {
      "epoch": 2.2990654205607477,
      "grad_norm": 4.190512180328369,
      "learning_rate": 1.4829032517260489e-05,
      "loss": 3.67,
      "step": 123
    },
    {
      "epoch": 2.3551401869158877,
      "grad_norm": 3.286802053451538,
      "learning_rate": 1.268078052756531e-05,
      "loss": 3.6418,
      "step": 126
    },
    {
      "epoch": 2.411214953271028,
      "grad_norm": 3.205436944961548,
      "learning_rate": 1.0677866784522317e-05,
      "loss": 3.6929,
      "step": 129
    },
    {
      "epoch": 2.467289719626168,
      "grad_norm": 3.498103380203247,
      "learning_rate": 8.828091557690289e-06,
      "loss": 3.8541,
      "step": 132
    },
    {
      "epoch": 2.5233644859813085,
      "grad_norm": 3.3449270725250244,
      "learning_rate": 7.138658724641417e-06,
      "loss": 3.7771,
      "step": 135
    },
    {
      "epoch": 2.5794392523364484,
      "grad_norm": 3.2664265632629395,
      "learning_rate": 5.616147715740611e-06,
      "loss": 3.6785,
      "step": 138
    },
    {
      "epoch": 2.635514018691589,
      "grad_norm": 3.2811155319213867,
      "learning_rate": 4.266487890810256e-06,
      "loss": 3.7523,
      "step": 141
    },
    {
      "epoch": 2.691588785046729,
      "grad_norm": 3.3988234996795654,
      "learning_rate": 3.0949354474692937e-06,
      "loss": 3.6636,
      "step": 144
    },
    {
      "epoch": 2.7476635514018692,
      "grad_norm": 3.528200387954712,
      "learning_rate": 2.106052951076365e-06,
      "loss": 3.8593,
      "step": 147
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 3.478485107421875,
      "learning_rate": 1.303691565996712e-06,
      "loss": 3.7467,
      "step": 150
    },
    {
      "epoch": 2.803738317757009,
      "eval_loss": 0.9532889723777771,
      "eval_runtime": 1.8036,
      "eval_samples_per_second": 49.901,
      "eval_steps_per_second": 12.753,
      "step": 150
    },
    {
      "epoch": 2.8598130841121496,
      "grad_norm": 3.1623222827911377,
      "learning_rate": 6.909760573925561e-07,
      "loss": 3.7121,
      "step": 153
    },
    {
      "epoch": 2.9158878504672896,
      "grad_norm": 3.4083008766174316,
      "learning_rate": 2.702926219468882e-07,
      "loss": 3.6461,
      "step": 156
    },
    {
      "epoch": 2.97196261682243,
      "grad_norm": 3.622955322265625,
      "learning_rate": 4.3279594913447905e-08,
      "loss": 3.818,
      "step": 159
    }
  ],
  "logging_steps": 3,
  "max_steps": 161,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 4.000267220759347e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}