{
  "best_metric": 0.35508111119270325,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.032362459546925564,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006472491909385113,
      "grad_norm": 12.386811256408691,
      "learning_rate": 2e-05,
      "loss": 2.1618,
      "step": 1
    },
    {
      "epoch": 0.0006472491909385113,
      "eval_loss": 1.1013591289520264,
      "eval_runtime": 105.9515,
      "eval_samples_per_second": 24.568,
      "eval_steps_per_second": 3.077,
      "step": 1
    },
    {
      "epoch": 0.0012944983818770227,
      "grad_norm": 10.682132720947266,
      "learning_rate": 4e-05,
      "loss": 2.1263,
      "step": 2
    },
    {
      "epoch": 0.001941747572815534,
      "grad_norm": 7.8965067863464355,
      "learning_rate": 6e-05,
      "loss": 1.588,
      "step": 3
    },
    {
      "epoch": 0.0025889967637540453,
      "grad_norm": 12.606889724731445,
      "learning_rate": 8e-05,
      "loss": 1.5629,
      "step": 4
    },
    {
      "epoch": 0.003236245954692557,
      "grad_norm": 6.1731276512146,
      "learning_rate": 0.0001,
      "loss": 1.6082,
      "step": 5
    },
    {
      "epoch": 0.003883495145631068,
      "grad_norm": 5.269734859466553,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.3069,
      "step": 6
    },
    {
      "epoch": 0.004530744336569579,
      "grad_norm": 15.008581161499023,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.4322,
      "step": 7
    },
    {
      "epoch": 0.005177993527508091,
      "grad_norm": 7.973099708557129,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4821,
      "step": 8
    },
    {
      "epoch": 0.005825242718446602,
      "grad_norm": 4.92938756942749,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2722,
      "step": 9
    },
    {
      "epoch": 0.006472491909385114,
      "grad_norm": 7.114321708679199,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3121,
      "step": 10
    },
    {
      "epoch": 0.007119741100323625,
      "grad_norm": 5.484792709350586,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.3083,
      "step": 11
    },
    {
      "epoch": 0.007766990291262136,
      "grad_norm": 5.332705974578857,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.19,
      "step": 12
    },
    {
      "epoch": 0.008414239482200648,
      "grad_norm": 6.66576623916626,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3733,
      "step": 13
    },
    {
      "epoch": 0.009061488673139158,
      "grad_norm": 5.858701229095459,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3019,
      "step": 14
    },
    {
      "epoch": 0.009708737864077669,
      "grad_norm": 6.463413715362549,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.356,
      "step": 15
    },
    {
      "epoch": 0.010355987055016181,
      "grad_norm": 4.812952995300293,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2641,
      "step": 16
    },
    {
      "epoch": 0.011003236245954692,
      "grad_norm": 5.166619300842285,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.4067,
      "step": 17
    },
    {
      "epoch": 0.011650485436893204,
      "grad_norm": 4.101341724395752,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1359,
      "step": 18
    },
    {
      "epoch": 0.012297734627831715,
      "grad_norm": 5.182929039001465,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2996,
      "step": 19
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 4.8671464920043945,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1693,
      "step": 20
    },
    {
      "epoch": 0.013592233009708738,
      "grad_norm": 4.907355308532715,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1906,
      "step": 21
    },
    {
      "epoch": 0.01423948220064725,
      "grad_norm": 4.77469539642334,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.203,
      "step": 22
    },
    {
      "epoch": 0.01488673139158576,
      "grad_norm": 5.339026927947998,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3357,
      "step": 23
    },
    {
      "epoch": 0.015533980582524271,
      "grad_norm": 5.2934370040893555,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.3286,
      "step": 24
    },
    {
      "epoch": 0.016181229773462782,
      "grad_norm": 5.244269847869873,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2954,
      "step": 25
    },
    {
      "epoch": 0.016181229773462782,
      "eval_loss": 0.38691768050193787,
      "eval_runtime": 107.8238,
      "eval_samples_per_second": 24.141,
      "eval_steps_per_second": 3.023,
      "step": 25
    },
    {
      "epoch": 0.016828478964401296,
      "grad_norm": 5.934874057769775,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.2681,
      "step": 26
    },
    {
      "epoch": 0.017475728155339806,
      "grad_norm": 5.760540008544922,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.3412,
      "step": 27
    },
    {
      "epoch": 0.018122977346278317,
      "grad_norm": 5.337496280670166,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.2902,
      "step": 28
    },
    {
      "epoch": 0.018770226537216828,
      "grad_norm": 5.112076759338379,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.1409,
      "step": 29
    },
    {
      "epoch": 0.019417475728155338,
      "grad_norm": 5.294675827026367,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.1751,
      "step": 30
    },
    {
      "epoch": 0.020064724919093852,
      "grad_norm": 5.933514595031738,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3161,
      "step": 31
    },
    {
      "epoch": 0.020711974110032363,
      "grad_norm": 6.715687274932861,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3662,
      "step": 32
    },
    {
      "epoch": 0.021359223300970873,
      "grad_norm": 6.21199893951416,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.2211,
      "step": 33
    },
    {
      "epoch": 0.022006472491909384,
      "grad_norm": 7.3447794914245605,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.4038,
      "step": 34
    },
    {
      "epoch": 0.022653721682847898,
      "grad_norm": 6.385514259338379,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.2576,
      "step": 35
    },
    {
      "epoch": 0.02330097087378641,
      "grad_norm": 8.130139350891113,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.391,
      "step": 36
    },
    {
      "epoch": 0.02394822006472492,
      "grad_norm": 7.305758953094482,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.2573,
      "step": 37
    },
    {
      "epoch": 0.02459546925566343,
      "grad_norm": 7.050241470336914,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.3572,
      "step": 38
    },
    {
      "epoch": 0.02524271844660194,
      "grad_norm": 8.658832550048828,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5489,
      "step": 39
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 7.916935920715332,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.2835,
      "step": 40
    },
    {
      "epoch": 0.026537216828478965,
      "grad_norm": 8.260157585144043,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2949,
      "step": 41
    },
    {
      "epoch": 0.027184466019417475,
      "grad_norm": 7.884759902954102,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.1645,
      "step": 42
    },
    {
      "epoch": 0.027831715210355986,
      "grad_norm": 10.152740478515625,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.4604,
      "step": 43
    },
    {
      "epoch": 0.0284789644012945,
      "grad_norm": 9.72319221496582,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.4565,
      "step": 44
    },
    {
      "epoch": 0.02912621359223301,
      "grad_norm": 11.225317001342773,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.53,
      "step": 45
    },
    {
      "epoch": 0.02977346278317152,
      "grad_norm": 11.727689743041992,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3768,
      "step": 46
    },
    {
      "epoch": 0.030420711974110032,
      "grad_norm": 17.733081817626953,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.6249,
      "step": 47
    },
    {
      "epoch": 0.031067961165048542,
      "grad_norm": 12.744095802307129,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.2594,
      "step": 48
    },
    {
      "epoch": 0.03171521035598705,
      "grad_norm": 31.65728759765625,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.7199,
      "step": 49
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 48.377784729003906,
      "learning_rate": 0.0,
      "loss": 1.8259,
      "step": 50
    },
    {
      "epoch": 0.032362459546925564,
      "eval_loss": 0.35508111119270325,
      "eval_runtime": 107.785,
      "eval_samples_per_second": 24.15,
      "eval_steps_per_second": 3.025,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 3.917361458656051e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}