{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07272727272727272,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014545454545454545,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.014545454545454545,
      "eval_loss": NaN,
      "eval_runtime": 48.09,
      "eval_samples_per_second": 2.412,
      "eval_steps_per_second": 1.206,
      "step": 1
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.02909090909090909,
      "eval_loss": NaN,
      "eval_runtime": 1.1998,
      "eval_samples_per_second": 96.683,
      "eval_steps_per_second": 48.341,
      "step": 2
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.05818181818181818,
      "eval_loss": NaN,
      "eval_runtime": 1.2873,
      "eval_samples_per_second": 90.113,
      "eval_steps_per_second": 45.056,
      "step": 4
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 648596517027840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}