{
  "best_metric": 0.6067896485328674,
  "best_model_checkpoint": "BERT-WMM/run-1/checkpoint-134",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7384976525821596,
      "eval_loss": 0.6279828548431396,
      "eval_runtime": 1.9975,
      "eval_samples_per_second": 1066.325,
      "eval_steps_per_second": 67.083,
      "step": 67
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7474178403755869,
      "eval_loss": 0.6067896485328674,
      "eval_runtime": 2.1054,
      "eval_samples_per_second": 1011.689,
      "eval_steps_per_second": 63.646,
      "step": 134
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7666666666666667,
      "eval_loss": 0.6562522053718567,
      "eval_runtime": 2.0963,
      "eval_samples_per_second": 1016.071,
      "eval_steps_per_second": 63.922,
      "step": 201
    }
  ],
  "logging_steps": 500,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.954808592770953e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 128,
    "weight_decay": 0.0034350079187271854
  }
}