{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09183673469387756,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01020408163265306,
      "eval_loss": 2.5547358989715576,
      "eval_runtime": 10.9643,
      "eval_samples_per_second": 15.049,
      "eval_steps_per_second": 1.915,
      "step": 1
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 22.481250762939453,
      "learning_rate": 3e-05,
      "loss": 10.7284,
      "step": 3
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 8.63905143737793,
      "learning_rate": 6e-05,
      "loss": 9.5021,
      "step": 6
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 6.093153953552246,
      "learning_rate": 9e-05,
      "loss": 8.4335,
      "step": 9
    },
    {
      "epoch": 0.09183673469387756,
      "eval_loss": 1.867263674736023,
      "eval_runtime": 11.1356,
      "eval_samples_per_second": 14.817,
      "eval_steps_per_second": 1.886,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6765120092897280.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}