{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1467,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.02,
      "learning_rate": 3.2958418541240625e-05,
      "loss": 0.3262,
      "step": 500
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.5916837082481257e-05,
      "loss": 0.269,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "step": 1467,
      "total_flos": 37853410099200.0,
      "train_loss": 0.2859099426477558,
      "train_runtime": 448.5269,
      "train_samples_per_second": 13.069,
      "train_steps_per_second": 3.271
    }
  ],
  "logging_steps": 500,
  "max_steps": 1467,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 37853410099200.0,
  "trial_name": null,
  "trial_params": null
}