{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.10549218698490143,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021098437396980287,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0021098437396980287,
      "eval_loss": NaN,
      "eval_runtime": 1.4041,
      "eval_samples_per_second": 35.609,
      "eval_steps_per_second": 9.258,
      "step": 1
    },
    {
      "epoch": 0.004219687479396057,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006329531219094086,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.008439374958792115,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.010549218698490143,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.012659062438188172,
      "grad_norm": NaN,
      "learning_rate": 9.997539658034168e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0147689061778862,
      "grad_norm": NaN,
      "learning_rate": 9.990161322484486e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.01687874991758423,
      "grad_norm": NaN,
      "learning_rate": 9.977873061452552e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.018988593657282258,
      "grad_norm": NaN,
      "learning_rate": 9.96068831197139e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.021098437396980287,
      "grad_norm": NaN,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.023208281136678315,
      "grad_norm": NaN,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.025318124876376344,
      "grad_norm": NaN,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.027427968616074373,
      "grad_norm": NaN,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0295378123557724,
      "grad_norm": NaN,
      "learning_rate": 9.80216101690461e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.031647656095470426,
      "grad_norm": NaN,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03375749983516846,
      "grad_norm": NaN,
      "learning_rate": 9.705540090697575e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.035867343574866484,
      "grad_norm": NaN,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.037977187314564516,
      "grad_norm": NaN,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04008703105426254,
      "grad_norm": NaN,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.04219687479396057,
      "grad_norm": NaN,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0443067185336586,
      "grad_norm": NaN,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.04641656227335663,
      "grad_norm": NaN,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.048526406013054656,
      "grad_norm": NaN,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.05063624975275269,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05274609349245071,
      "grad_norm": NaN,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.05274609349245071,
      "eval_loss": NaN,
      "eval_runtime": 1.404,
      "eval_samples_per_second": 35.613,
      "eval_steps_per_second": 9.259,
      "step": 25
    },
    {
      "epoch": 0.054855937232148745,
      "grad_norm": NaN,
      "learning_rate": 8.957804998855866e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.05696578097184677,
      "grad_norm": NaN,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0590756247115448,
      "grad_norm": NaN,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.06118546845124283,
      "grad_norm": NaN,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.06329531219094085,
      "grad_norm": NaN,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.06540515593063889,
      "grad_norm": NaN,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.06751499967033692,
      "grad_norm": NaN,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.06962484341003494,
      "grad_norm": NaN,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.07173468714973297,
      "grad_norm": NaN,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.073844530889431,
      "grad_norm": NaN,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.07595437462912903,
      "grad_norm": NaN,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.07806421836882706,
      "grad_norm": NaN,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.08017406210852508,
      "grad_norm": NaN,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.08228390584822312,
      "grad_norm": NaN,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.08439374958792115,
      "grad_norm": NaN,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.08650359332761917,
      "grad_norm": NaN,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0886134370673172,
      "grad_norm": NaN,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.09072328080701524,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.09283312454671326,
      "grad_norm": NaN,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.09494296828641129,
      "grad_norm": NaN,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.09705281202610931,
      "grad_norm": NaN,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.09916265576580735,
      "grad_norm": NaN,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.10127249950550538,
      "grad_norm": NaN,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.1033823432452034,
      "grad_norm": NaN,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.10549218698490143,
      "grad_norm": NaN,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.10549218698490143,
      "eval_loss": NaN,
      "eval_runtime": 1.4035,
      "eval_samples_per_second": 35.625,
      "eval_steps_per_second": 9.262,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.625815332741448e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}