{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 1.4265,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.566110134124756,
      "eval_runtime": 0.2634,
      "eval_samples_per_second": 15.184,
      "eval_steps_per_second": 3.796,
      "step": 1
    },
    {
      "epoch": 1.0,
      "step": 1,
      "total_flos": 32602467598336.0,
      "train_loss": 1.4264578819274902,
      "train_runtime": 1.98,
      "train_samples_per_second": 2.02,
      "train_steps_per_second": 0.505
    }
  ],
  "logging_steps": 5,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 32602467598336.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}