{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0104412260020208,
  "eval_steps": 750,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.01,
      "learning_rate": 4.949460916442048e-05,
      "loss": 5.3025,
      "step": 750
    },
    {
      "epoch": 1.01,
      "eval_loss": 4.010455131530762,
      "eval_runtime": 85.2403,
      "eval_samples_per_second": 58.658,
      "eval_steps_per_second": 0.927,
      "step": 750
    }
  ],
  "logging_steps": 750,
  "max_steps": 74200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 750,
  "total_flos": 3.245985557508096e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}