{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001196911967124818,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "grad_norm": 37.3111572265625,
      "learning_rate": 2e-05,
      "loss": 12.814,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 34.40701675415039,
      "learning_rate": 4e-05,
      "loss": 12.7548,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 34.153663635253906,
      "learning_rate": 6e-05,
      "loss": 13.7805,
      "step": 3
    },
    {
      "epoch": 0.0001196911967124818,
      "eval_loss": 13.004719734191895,
      "eval_runtime": 901.8184,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 5.852,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 786064805462016.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}