{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0559662090813093,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.06,
      "learning_rate": 1.0559662090813095e-06,
      "loss": 4.6112,
      "step": 1000
    },
    {
      "epoch": 1.06,
      "eval_accuracy": 0.034851485148514855,
      "eval_loss": 4.575930118560791,
      "eval_runtime": 157.053,
      "eval_samples_per_second": 96.464,
      "eval_steps_per_second": 6.03,
      "step": 1000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 473500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 500,
  "save_steps": 1000,
  "total_flos": 4.963267430656819e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}