{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4210526315789473,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.135121657280251e-05,
      "learning_rate": 0.0001,
      "loss": 35.9669,
      "step": 5
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.358254812071195e-11,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 2.4210526315789473,
      "step": 12,
      "total_flos": 0.0,
      "train_loss": 14.98622005609279,
      "train_runtime": 189.4123,
      "train_samples_per_second": 2.376,
      "train_steps_per_second": 0.063
    }
  ],
  "logging_steps": 5,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}