{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.1902439024390246,
  "eval_steps": 25,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07804878048780488,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 12.9666,
      "step": 1
    },
    {
      "epoch": 0.07804878048780488,
      "eval_loss": NaN,
      "eval_runtime": 4.9702,
      "eval_samples_per_second": 10.06,
      "eval_steps_per_second": 2.616,
      "step": 1
    },
    {
      "epoch": 0.15609756097560976,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.23414634146341465,
      "grad_norm": NaN,
      "learning_rate": 9.983788698441369e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.3121951219512195,
      "grad_norm": NaN,
      "learning_rate": 9.935271596564688e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": NaN,
      "learning_rate": 9.854798261200746e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4682926829268293,
      "grad_norm": NaN,
      "learning_rate": 9.74294850457488e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5463414634146342,
      "grad_norm": NaN,
      "learning_rate": 9.600528206746612e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.624390243902439,
      "grad_norm": NaN,
      "learning_rate": 9.428563509225347e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.7024390243902439,
      "grad_norm": NaN,
      "learning_rate": 9.22829342159729e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": NaN,
      "learning_rate": 9.001160894432978e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.8585365853658536,
      "grad_norm": NaN,
      "learning_rate": 8.74880242279536e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.9365853658536586,
      "grad_norm": NaN,
      "learning_rate": 8.473036255255366e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.0634146341463415,
      "grad_norm": NaN,
      "learning_rate": 8.175849293369291e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.1414634146341462,
      "grad_norm": NaN,
      "learning_rate": 7.859382776007543e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": NaN,
      "learning_rate": 7.525916851679529e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.2975609756097561,
      "grad_norm": NaN,
      "learning_rate": 7.177854150011389e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.3756097560975609,
      "grad_norm": NaN,
      "learning_rate": 6.817702470744477e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.4536585365853658,
      "grad_norm": NaN,
      "learning_rate": 6.448056714980767e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.5317073170731708,
      "grad_norm": NaN,
      "learning_rate": 6.071580188860955e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.6097560975609757,
      "grad_norm": NaN,
      "learning_rate": 5.690985414382668e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.6878048780487804,
      "grad_norm": NaN,
      "learning_rate": 5.3090145856173346e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.7658536585365854,
      "grad_norm": NaN,
      "learning_rate": 4.9284198111390456e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.84390243902439,
      "grad_norm": NaN,
      "learning_rate": 4.551943285019234e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.921951219512195,
      "grad_norm": NaN,
      "learning_rate": 4.182297529255525e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 2.048780487804878,
      "grad_norm": NaN,
      "learning_rate": 3.822145849988612e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 2.048780487804878,
      "eval_loss": NaN,
      "eval_runtime": 5.2865,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 2.459,
      "step": 25
    },
    {
      "epoch": 2.126829268292683,
      "grad_norm": NaN,
      "learning_rate": 3.474083148320469e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 2.204878048780488,
      "grad_norm": NaN,
      "learning_rate": 3.1406172239924584e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 2.2829268292682925,
      "grad_norm": NaN,
      "learning_rate": 2.8241507066307104e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 2.3609756097560974,
      "grad_norm": NaN,
      "learning_rate": 2.5269637447446348e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": NaN,
      "learning_rate": 2.2511975772046403e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 2.5170731707317073,
      "grad_norm": NaN,
      "learning_rate": 1.9988391055670233e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 2.5951219512195123,
      "grad_norm": NaN,
      "learning_rate": 1.771706578402711e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 2.6731707317073172,
      "grad_norm": NaN,
      "learning_rate": 1.5714364907746536e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 2.7512195121951217,
      "grad_norm": NaN,
      "learning_rate": 1.3994717932533891e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 2.8292682926829267,
      "grad_norm": NaN,
      "learning_rate": 1.257051495425121e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 2.9073170731707316,
      "grad_norm": NaN,
      "learning_rate": 1.1452017387992552e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 3.0341463414634147,
      "grad_norm": NaN,
      "learning_rate": 1.064728403435312e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 3.1121951219512196,
      "grad_norm": NaN,
      "learning_rate": 1.0162113015586309e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 3.1902439024390246,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.33933996183126e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}