{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6666666666666665,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.67,
      "learning_rate": 0.00018,
      "loss": 2.6813,
      "step": 3
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012,
      "loss": 2.489,
      "step": 6
    },
    {
      "epoch": 2.0,
      "learning_rate": 6e-05,
      "loss": 2.04,
      "step": 9
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0,
      "loss": 1.722,
      "step": 12
    }
  ],
  "logging_steps": 3,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2099029034926080.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}