{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999,
  "global_step": 999,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5,
      "learning_rate": 2.4974974974974976e-05,
      "loss": 1.3409,
      "step": 500
    },
    {
      "epoch": 3.0,
      "step": 999,
      "total_flos": 1.4606682885095424e+16,
      "train_loss": 1.0714508148285005,
      "train_runtime": 1254.6583,
      "train_samples_per_second": 19.129,
      "train_steps_per_second": 0.796
    }
  ],
  "max_steps": 999,
  "num_train_epochs": 3,
  "total_flos": 1.4606682885095424e+16,
  "trial_name": null,
  "trial_params": null
}