{
  "best_metric": 0.4824335154846928,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 12.893019676208496,
      "learning_rate": 1.0194042691078977e-05,
      "loss": 0.6006,
      "step": 500
    },
    {
      "epoch": 0.47,
      "grad_norm": 15.821282386779785,
      "learning_rate": 8.844195936433985e-06,
      "loss": 0.5451,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "grad_norm": 13.875489234924316,
      "learning_rate": 7.494349181788993e-06,
      "loss": 0.5134,
      "step": 1500
    },
    {
      "epoch": 0.94,
      "grad_norm": 27.784305572509766,
      "learning_rate": 6.144502427144001e-06,
      "loss": 0.5264,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4990427494049072,
      "eval_matthews_correlation": 0.4824335154846928,
      "eval_runtime": 0.7747,
      "eval_samples_per_second": 1346.334,
      "eval_steps_per_second": 85.195,
      "step": 2138
    }
  ],
  "logging_steps": 500,
  "max_steps": 4276,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 32633550639216.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.1543889445723968e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 4,
    "seed": 11
  }
}