run-3/checkpoint-402/trainer_state.json

{
  "best_metric": 0.5497693861041112,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-402",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 402,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5051767230033875,
      "eval_matthews_correlation": 0.4122249494973531,
      "eval_runtime": 0.3394,
      "eval_samples_per_second": 3073.178,
      "eval_steps_per_second": 194.468,
      "step": 134
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.46091583371162415,
      "eval_matthews_correlation": 0.49531265709783606,
      "eval_runtime": 0.3621,
      "eval_samples_per_second": 2880.741,
      "eval_steps_per_second": 182.29,
      "step": 268
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5372118353843689,
      "eval_matthews_correlation": 0.5497693861041112,
      "eval_runtime": 0.3562,
      "eval_samples_per_second": 2928.06,
      "eval_steps_per_second": 185.285,
      "step": 402
    }
  ],
  "logging_steps": 500,
  "max_steps": 670,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.239666749738152e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 3
  }
}