{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.036003600360036005,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0072007200720072,
      "grad_norm": 18.639007568359375,
      "learning_rate": 1e-05,
      "loss": 15.1061,
      "step": 1
    },
    {
      "epoch": 0.0072007200720072,
      "eval_loss": 16.10308837890625,
      "eval_runtime": 174.0805,
      "eval_samples_per_second": 1.344,
      "eval_steps_per_second": 0.672,
      "step": 1
    },
    {
      "epoch": 0.0144014401440144,
      "grad_norm": 19.95916175842285,
      "learning_rate": 2e-05,
      "loss": 16.5652,
      "step": 2
    },
    {
      "epoch": 0.0144014401440144,
      "eval_loss": 15.889203071594238,
      "eval_runtime": 21.9183,
      "eval_samples_per_second": 10.676,
      "eval_steps_per_second": 5.338,
      "step": 2
    },
    {
      "epoch": 0.021602160216021602,
      "grad_norm": 19.98402214050293,
      "learning_rate": 3e-05,
      "loss": 16.2942,
      "step": 3
    },
    {
      "epoch": 0.0288028802880288,
      "grad_norm": 19.017255783081055,
      "learning_rate": 4e-05,
      "loss": 15.9926,
      "step": 4
    },
    {
      "epoch": 0.0288028802880288,
      "eval_loss": 14.651693344116211,
      "eval_runtime": 21.9058,
      "eval_samples_per_second": 10.682,
      "eval_steps_per_second": 5.341,
      "step": 4
    },
    {
      "epoch": 0.036003600360036005,
      "grad_norm": 20.25791358947754,
      "learning_rate": 5e-05,
      "loss": 15.3253,
      "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": 6875518618042368.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}