run-0/checkpoint-804/trainer_state.json

{
  "best_metric": 0.4797446434500675,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-804",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.49786698818206787,
      "eval_matthews_correlation": 0.4184145751988745,
      "eval_runtime": 0.7269,
      "eval_samples_per_second": 1434.823,
      "eval_steps_per_second": 90.794,
      "step": 268
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.774138267483819e-06,
      "loss": 0.4832,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4944550395011902,
      "eval_matthews_correlation": 0.4677857815103733,
      "eval_runtime": 0.718,
      "eval_samples_per_second": 1452.645,
      "eval_steps_per_second": 91.922,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5118187665939331,
      "eval_matthews_correlation": 0.4797446434500675,
      "eval_runtime": 1.1155,
      "eval_samples_per_second": 935.047,
      "eval_steps_per_second": 59.169,
      "step": 804
    }
  ],
  "logging_steps": 500,
  "max_steps": 804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 95617141643160.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.2626339365319049e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 32,
    "seed": 26
  }
}