run-2/checkpoint-56/trainer_state.json

{
  "best_metric": 0.2047253529986547,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-56",
  "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": 0.6130949854850769,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.8143,
      "eval_samples_per_second": 1280.789,
      "eval_steps_per_second": 81.047,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5834124088287354,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.7766,
      "eval_samples_per_second": 1343.102,
      "eval_steps_per_second": 84.99,
      "step": 28
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5700901746749878,
      "eval_matthews_correlation": 0.1077683109552469,
      "eval_runtime": 0.757,
      "eval_samples_per_second": 1377.871,
      "eval_steps_per_second": 87.19,
      "step": 42
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5696095824241638,
      "eval_matthews_correlation": 0.2047253529986547,
      "eval_runtime": 0.7553,
      "eval_samples_per_second": 1380.933,
      "eval_steps_per_second": 87.384,
      "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": 4.734214749417639e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 64,
    "seed": 19
  }
}