run-1/checkpoint-536/trainer_state.json

{
  "best_metric": 0.0,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-134",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6137625575065613,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 36.6021,
      "eval_samples_per_second": 28.496,
      "eval_steps_per_second": 1.803,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5987810492515564,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 36.8222,
      "eval_samples_per_second": 28.325,
      "eval_steps_per_second": 1.792,
      "step": 268
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5791416168212891,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 37.6773,
      "eval_samples_per_second": 27.682,
      "eval_steps_per_second": 1.752,
      "step": 402
    },
    {
      "epoch": 3.73,
      "grad_norm": 2.049774408340454,
      "learning_rate": 4.1397348321527435e-07,
      "loss": 0.5959,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5682925581932068,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 37.2686,
      "eval_samples_per_second": 27.986,
      "eval_steps_per_second": 1.771,
      "step": 536
    }
  ],
  "logging_steps": 500,
  "max_steps": 670,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 209861476320768.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.631542551495493e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 6
  }
}