{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12421588721197441,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 9.958592132505176e-05,
      "loss": 1.3838,
      "step": 500
    },
    {
      "epoch": 0.12,
      "eval_loss": 1.3269665241241455,
      "eval_runtime": 63.2116,
      "eval_samples_per_second": 255.634,
      "eval_steps_per_second": 15.978,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 120750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 5001938240274432.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}