{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03076923076923077,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 1.892773151397705,
      "eval_runtime": 1.9218,
      "eval_samples_per_second": 59.321,
      "eval_steps_per_second": 3.122,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 14.950183868408203,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.7711,
      "step": 10
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 1.1033935546875,
      "eval_runtime": 1.8218,
      "eval_samples_per_second": 62.575,
      "eval_steps_per_second": 3.293,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 325,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 890943653806080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}