{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019603038470963,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0039206076941926,
      "grad_norm": 23.591537475585938,
      "learning_rate": 1e-05,
      "loss": 8.6701,
      "step": 1
    },
    {
      "epoch": 0.0039206076941926,
      "eval_loss": 8.404369354248047,
      "eval_runtime": 39.4659,
      "eval_samples_per_second": 10.895,
      "eval_steps_per_second": 5.448,
      "step": 1
    },
    {
      "epoch": 0.0078412153883852,
      "grad_norm": 22.02801513671875,
      "learning_rate": 2e-05,
      "loss": 8.7647,
      "step": 2
    },
    {
      "epoch": 0.0078412153883852,
      "eval_loss": 8.168349266052246,
      "eval_runtime": 9.0179,
      "eval_samples_per_second": 47.683,
      "eval_steps_per_second": 23.841,
      "step": 2
    },
    {
      "epoch": 0.0117618230825778,
      "grad_norm": 22.62014389038086,
      "learning_rate": 3e-05,
      "loss": 8.187,
      "step": 3
    },
    {
      "epoch": 0.0156824307767704,
      "grad_norm": 20.565902709960938,
      "learning_rate": 4e-05,
      "loss": 7.4929,
      "step": 4
    },
    {
      "epoch": 0.0156824307767704,
      "eval_loss": 7.563743591308594,
      "eval_runtime": 8.9544,
      "eval_samples_per_second": 48.021,
      "eval_steps_per_second": 24.011,
      "step": 4
    },
    {
      "epoch": 0.019603038470963,
      "grad_norm": 20.374956130981445,
      "learning_rate": 5e-05,
      "loss": 7.339,
      "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": 978955586764800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}