{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 8.375,
      "learning_rate": 7e-06,
      "loss": 1.9758,
      "step": 10
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.59375,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 1.0883,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.875,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.9561,
      "step": 30
    },
    {
      "epoch": 3.0,
      "step": 30,
      "total_flos": 7897183093260288.0,
      "train_loss": 1.3400681177775065,
      "train_runtime": 125.799,
      "train_samples_per_second": 3.649,
      "train_steps_per_second": 0.238
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7897183093260288.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}