run-4/checkpoint-270/trainer_state.json

{
  "best_metric": 0.0,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6213765144348145,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.9261,
      "eval_samples_per_second": 1126.256,
      "eval_steps_per_second": 71.268,
      "step": 54
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6132947206497192,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.1072,
      "eval_samples_per_second": 941.986,
      "eval_steps_per_second": 59.608,
      "step": 108
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6101319789886475,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.0236,
      "eval_samples_per_second": 1018.958,
      "eval_steps_per_second": 64.479,
      "step": 162
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6080467104911804,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.9472,
      "eval_samples_per_second": 1101.131,
      "eval_steps_per_second": 69.678,
      "step": 216
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.607087254524231,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.0206,
      "eval_samples_per_second": 1021.943,
      "eval_steps_per_second": 64.668,
      "step": 270
    }
  ],
  "logging_steps": 500,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.064609255788969e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 1
  }
}