{
  "best_metric": 1.4934452772140503,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.001394583437927091,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7891668758541825e-05,
      "eval_loss": 2.138502359390259,
      "eval_runtime": 539.9687,
      "eval_samples_per_second": 27.959,
      "eval_steps_per_second": 6.991,
      "step": 1
    },
    {
      "epoch": 0.0002789166875854182,
      "grad_norm": 3.119084358215332,
      "learning_rate": 5.05e-06,
      "loss": 2.1448,
      "step": 10
    },
    {
      "epoch": 0.0005578333751708364,
      "grad_norm": 2.9193804264068604,
      "learning_rate": 1.01e-05,
      "loss": 1.8834,
      "step": 20
    },
    {
      "epoch": 0.0008367500627562547,
      "grad_norm": 3.0759785175323486,
      "learning_rate": 9.538888888888889e-06,
      "loss": 1.7763,
      "step": 30
    },
    {
      "epoch": 0.0011156667503416729,
      "grad_norm": 2.9843831062316895,
      "learning_rate": 8.977777777777778e-06,
      "loss": 1.6058,
      "step": 40
    },
    {
      "epoch": 0.001394583437927091,
      "grad_norm": 5.683198928833008,
      "learning_rate": 8.416666666666667e-06,
      "loss": 1.5341,
      "step": 50
    },
    {
      "epoch": 0.001394583437927091,
      "eval_loss": 1.4934452772140503,
      "eval_runtime": 540.9009,
      "eval_samples_per_second": 27.911,
      "eval_steps_per_second": 6.979,
      "step": 50
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.131385184059392e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}