{
  "best_metric": 2.7653255462646484,
  "best_model_checkpoint": "out/checkpoint-1",
  "epoch": 0.0006538084341288003,
  "eval_steps": 1,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 2.716193199157715,
      "learning_rate": 0.0002,
      "loss": 3.0588,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 2.7653255462646484,
      "eval_runtime": 7085.2021,
      "eval_samples_per_second": 0.865,
      "eval_steps_per_second": 0.216,
      "step": 1
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "total_flos": 6623040897024.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}