{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11379800853485064,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02275960170697013,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.02275960170697013,
      "eval_loss": NaN,
      "eval_runtime": 40.2373,
      "eval_samples_per_second": 1.839,
      "eval_steps_per_second": 0.92,
      "step": 1
    },
    {
      "epoch": 0.04551920341394026,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.04551920341394026,
      "eval_loss": NaN,
      "eval_runtime": 1.5807,
      "eval_samples_per_second": 46.815,
      "eval_steps_per_second": 23.407,
      "step": 2
    },
    {
      "epoch": 0.06827880512091039,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.09103840682788052,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.09103840682788052,
      "eval_loss": NaN,
      "eval_runtime": 1.58,
      "eval_samples_per_second": 46.837,
      "eval_steps_per_second": 23.418,
      "step": 4
    },
    {
      "epoch": 0.11379800853485064,
      "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": 3485272092180480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}