{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.5384615384615383,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06153846153846154,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": NaN,
      "eval_runtime": 1.4338,
      "eval_samples_per_second": 34.873,
      "eval_steps_per_second": 9.067,
      "step": 1
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": NaN,
      "learning_rate": 9.98995095380419e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": NaN,
      "learning_rate": 9.959848696696512e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": NaN,
      "learning_rate": 9.90982767266464e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": NaN,
      "learning_rate": 9.840111287744695e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": NaN,
      "learning_rate": 9.751010912235635e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": NaN,
      "learning_rate": 9.642924490043929e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": NaN,
      "learning_rate": 9.516334761369466e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": NaN,
      "learning_rate": 9.371807106670628e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": NaN,
      "learning_rate": 9.209987021537921e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": NaN,
      "learning_rate": 9.031597233753974e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8,
      "grad_norm": NaN,
      "learning_rate": 8.83743447541581e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": NaN,
      "learning_rate": 8.628365924535892e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": NaN,
      "learning_rate": 8.405325332014611e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": NaN,
      "learning_rate": 8.169308851282099e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": NaN,
      "learning_rate": 7.921370589235178e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.1076923076923078,
      "grad_norm": NaN,
      "learning_rate": 7.662617898340078e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.1692307692307693,
      "grad_norm": NaN,
      "learning_rate": 7.394206430927509e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": NaN,
      "learning_rate": 7.117334977768807e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.2923076923076924,
      "grad_norm": NaN,
      "learning_rate": 6.833240113985353e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.353846153846154,
      "grad_norm": NaN,
      "learning_rate": 6.543190676203878e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": NaN,
      "learning_rate": 6.248482095624086e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.476923076923077,
      "grad_norm": NaN,
      "learning_rate": 5.950430612308444e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": NaN,
      "learning_rate": 5.650367396534536e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": NaN,
      "eval_runtime": 0.6119,
      "eval_samples_per_second": 81.718,
      "eval_steps_per_second": 21.247,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 49,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1506187337728e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}