{
  "best_metric": 0.8369658589363098,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.4357298474945534,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002178649237472767,
      "eval_loss": 1.642710566520691,
      "eval_runtime": 11.0208,
      "eval_samples_per_second": 13.157,
      "eval_steps_per_second": 3.357,
      "step": 1
    },
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 13.529788970947266,
      "learning_rate": 5.095e-06,
      "loss": 1.5568,
      "step": 10
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 11.73664379119873,
      "learning_rate": 1.019e-05,
      "loss": 1.3614,
      "step": 20
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 15.36020565032959,
      "learning_rate": 9.623888888888889e-06,
      "loss": 1.1538,
      "step": 30
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 16.68719482421875,
      "learning_rate": 9.057777777777777e-06,
      "loss": 0.9726,
      "step": 40
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 8.945978164672852,
      "learning_rate": 8.491666666666667e-06,
      "loss": 0.8609,
      "step": 50
    },
    {
      "epoch": 0.10893246187363835,
      "eval_loss": 1.0293898582458496,
      "eval_runtime": 11.263,
      "eval_samples_per_second": 12.874,
      "eval_steps_per_second": 3.285,
      "step": 50
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 8.820780754089355,
      "learning_rate": 7.925555555555557e-06,
      "loss": 1.1589,
      "step": 60
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 7.298919677734375,
      "learning_rate": 7.359444444444445e-06,
      "loss": 0.9633,
      "step": 70
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 6.904092311859131,
      "learning_rate": 6.793333333333333e-06,
      "loss": 0.8975,
      "step": 80
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 9.39885425567627,
      "learning_rate": 6.227222222222223e-06,
      "loss": 0.8465,
      "step": 90
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 9.127683639526367,
      "learning_rate": 5.661111111111112e-06,
      "loss": 0.751,
      "step": 100
    },
    {
      "epoch": 0.2178649237472767,
      "eval_loss": 0.9036096930503845,
      "eval_runtime": 11.2686,
      "eval_samples_per_second": 12.868,
      "eval_steps_per_second": 3.283,
      "step": 100
    },
    {
      "epoch": 0.23965141612200436,
      "grad_norm": 7.476004123687744,
      "learning_rate": 5.095e-06,
      "loss": 1.0529,
      "step": 110
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 7.453296184539795,
      "learning_rate": 4.5288888888888885e-06,
      "loss": 0.9474,
      "step": 120
    },
    {
      "epoch": 0.28322440087145967,
      "grad_norm": 8.616524696350098,
      "learning_rate": 3.9627777777777784e-06,
      "loss": 0.7555,
      "step": 130
    },
    {
      "epoch": 0.30501089324618735,
      "grad_norm": 9.001409530639648,
      "learning_rate": 3.3966666666666666e-06,
      "loss": 0.8331,
      "step": 140
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 9.718732833862305,
      "learning_rate": 2.830555555555556e-06,
      "loss": 0.7389,
      "step": 150
    },
    {
      "epoch": 0.32679738562091504,
      "eval_loss": 0.8491891622543335,
      "eval_runtime": 11.2774,
      "eval_samples_per_second": 12.858,
      "eval_steps_per_second": 3.281,
      "step": 150
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 6.21028995513916,
      "learning_rate": 2.2644444444444443e-06,
      "loss": 1.008,
      "step": 160
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 7.034985542297363,
      "learning_rate": 1.6983333333333333e-06,
      "loss": 0.8855,
      "step": 170
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 7.719512462615967,
      "learning_rate": 1.1322222222222221e-06,
      "loss": 0.8906,
      "step": 180
    },
    {
      "epoch": 0.4139433551198257,
      "grad_norm": 5.853115081787109,
      "learning_rate": 5.661111111111111e-07,
      "loss": 0.8076,
      "step": 190
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 12.761053085327148,
      "learning_rate": 0.0,
      "loss": 0.6258,
      "step": 200
    },
    {
      "epoch": 0.4357298474945534,
      "eval_loss": 0.8369658589363098,
      "eval_runtime": 11.2719,
      "eval_samples_per_second": 12.864,
      "eval_steps_per_second": 3.282,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 5.35744505488343e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}