{
  "best_metric": 0.47921629302778096,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2138,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "grad_norm": 17.90995979309082,
      "learning_rate": 1.8573493164868257e-05,
      "loss": 0.6076,
      "step": 500
    },
    {
      "epoch": 0.47,
      "grad_norm": 25.591594696044922,
      "learning_rate": 1.700319445292471e-05,
      "loss": 0.5721,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "grad_norm": 17.508258819580078,
      "learning_rate": 1.5432895740981165e-05,
      "loss": 0.5514,
      "step": 1500
    },
    {
      "epoch": 0.94,
      "grad_norm": 47.17720031738281,
      "learning_rate": 1.3862597029037618e-05,
      "loss": 0.5529,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4856245219707489,
      "eval_matthews_correlation": 0.47921629302778096,
      "eval_runtime": 0.8291,
      "eval_samples_per_second": 1258.047,
      "eval_steps_per_second": 79.608,
      "step": 2138
    }
  ],
  "logging_steps": 500,
  "max_steps": 6414,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 83994162312648.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.01437918768118e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 4,
    "seed": 9
  }
}