{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 2.5300133055281324,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.485,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.22973599645498,
      "learning_rate": 7.795964517353734e-06,
      "loss": 0.2244,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.4935206101620415,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.2128,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.5336749374789689,
      "learning_rate": 1.4033009983067454e-06,
      "loss": 0.1599,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7698705961108752,
      "learning_rate": 1.2179748700879013e-08,
      "loss": 0.1878,
      "step": 50
    },
    {
      "epoch": 1.0,
      "step": 50,
      "total_flos": 1645060325376.0,
      "train_loss": 0.25399806499481203,
      "train_runtime": 90.6551,
      "train_samples_per_second": 17.649,
      "train_steps_per_second": 0.552
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1645060325376.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}