{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17857142857142858,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 3.328125,
      "learning_rate": 0.0001392329191677441,
      "loss": 2.2103,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 2.171875,
      "learning_rate": 0.00013910794129812952,
      "loss": 1.9707,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 1.859375,
      "learning_rate": 0.00013888701215922298,
      "loss": 1.824,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00013857044074040234,
      "loss": 1.8183,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.8671875,
      "learning_rate": 0.0001381586697954222,
      "loss": 1.8218,
      "step": 25
    },
    {
      "epoch": 0.17857142857142858,
      "eval_loss": 1.836487054824829,
      "eval_runtime": 0.3178,
      "eval_samples_per_second": 12.586,
      "eval_steps_per_second": 12.586,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.48916600766464e+16,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}