{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.18518518518518517,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009259259259259259,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "eval_loss": NaN,
      "eval_runtime": 9.2823,
      "eval_samples_per_second": 4.956,
      "eval_steps_per_second": 2.478,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.6533,
      "step": 5
    },
    {
      "epoch": 0.046296296296296294,
      "eval_loss": NaN,
      "eval_runtime": 8.2615,
      "eval_samples_per_second": 5.568,
      "eval_steps_per_second": 2.784,
      "step": 5
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.09259259259259259,
      "eval_loss": NaN,
      "eval_runtime": 8.2876,
      "eval_samples_per_second": 5.55,
      "eval_steps_per_second": 2.775,
      "step": 10
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1388888888888889,
      "eval_loss": NaN,
      "eval_runtime": 8.2739,
      "eval_samples_per_second": 5.56,
      "eval_steps_per_second": 2.78,
      "step": 15
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": NaN,
      "eval_runtime": 8.2781,
      "eval_samples_per_second": 5.557,
      "eval_steps_per_second": 2.778,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9995866236518400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}