{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5333333333333333,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.53,
      "learning_rate": 9.348986125933833e-06,
      "loss": 0.8147,
      "step": 500
    },
    {
      "epoch": 0.53,
      "eval_loss": 0.15259185433387756,
      "eval_runtime": 889.5833,
      "eval_samples_per_second": 11.241,
      "eval_steps_per_second": 2.81,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 937,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.7336836816896e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}