{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43,
      "grad_norm": 1.065733790397644,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4771,
      "step": 25
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8414725661277771,
      "learning_rate": 1.026015713086418e-05,
      "loss": 0.7992,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.633315920829773,
      "eval_runtime": 4.1867,
      "eval_samples_per_second": 27.468,
      "eval_steps_per_second": 3.583,
      "step": 58
    }
  ],
  "logging_steps": 25,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 6454112856760320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}