{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.909090909090909,
  "eval_steps": 500,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.73,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.3825,
      "step": 2
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.3294,
      "step": 4
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.2511,
      "step": 6
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0,
      "loss": 1.2046,
      "step": 8
    }
  ],
  "logging_steps": 2,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2601413372805120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}