run-3/checkpoint-56/trainer_state.json

{
  "best_metric": 0.018148342420931135,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-42",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 56,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6899405121803284,
      "eval_matthews_correlation": -0.0012450335596717033,
      "eval_runtime": 0.5096,
      "eval_samples_per_second": 2046.79,
      "eval_steps_per_second": 129.519,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6814213991165161,
      "eval_matthews_correlation": -0.002640723954860937,
      "eval_runtime": 0.5573,
      "eval_samples_per_second": 1871.622,
      "eval_steps_per_second": 118.434,
      "step": 28
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6765669584274292,
      "eval_matthews_correlation": 0.018148342420931135,
      "eval_runtime": 0.5031,
      "eval_samples_per_second": 2073.338,
      "eval_steps_per_second": 131.199,
      "step": 42
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6748957633972168,
      "eval_matthews_correlation": -0.020702674026557004,
      "eval_runtime": 0.5099,
      "eval_samples_per_second": 2045.315,
      "eval_steps_per_second": 129.426,
      "step": 56
    }
  ],
  "logging_steps": 500,
  "max_steps": 56,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.3575082617683651e-06,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 64,
    "seed": 16
  }
}