{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.168157423971378,
  "eval_steps": 500,
  "global_step": 1980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.6688,
      "step": 220
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0002,
      "loss": 0.9324,
      "step": 440
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0002,
      "loss": 0.416,
      "step": 660
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.0002,
      "loss": 0.2126,
      "step": 880
    },
    {
      "epoch": 7.87,
      "learning_rate": 0.0002,
      "loss": 0.1331,
      "step": 1100
    },
    {
      "epoch": 9.45,
      "learning_rate": 0.0002,
      "loss": 0.1011,
      "step": 1320
    },
    {
      "epoch": 11.02,
      "learning_rate": 0.0002,
      "loss": 0.0861,
      "step": 1540
    },
    {
      "epoch": 12.59,
      "learning_rate": 0.0002,
      "loss": 0.0725,
      "step": 1760
    },
    {
      "epoch": 14.17,
      "learning_rate": 0.0002,
      "loss": 0.0713,
      "step": 1980
    }
  ],
  "logging_steps": 220,
  "max_steps": 2200,
  "num_train_epochs": 16,
  "save_steps": 220,
  "total_flos": 9.239634211022438e+16,
  "trial_name": null,
  "trial_params": null
}