run-1/checkpoint-216/trainer_state.json

{
  "best_metric": 0.31087774676686925,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-216",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 216,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5931112766265869,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 30.6162,
      "eval_samples_per_second": 34.067,
      "eval_steps_per_second": 2.156,
      "step": 54
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.556400716304779,
      "eval_matthews_correlation": 0.25285211471364255,
      "eval_runtime": 30.8319,
      "eval_samples_per_second": 33.829,
      "eval_steps_per_second": 2.141,
      "step": 108
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.561941921710968,
      "eval_matthews_correlation": 0.31016392231638445,
      "eval_runtime": 30.9625,
      "eval_samples_per_second": 33.686,
      "eval_steps_per_second": 2.132,
      "step": 162
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5864373445510864,
      "eval_matthews_correlation": 0.31087774676686925,
      "eval_runtime": 37.4586,
      "eval_samples_per_second": 27.844,
      "eval_steps_per_second": 1.762,
      "step": 216
    }
  ],
  "logging_steps": 500,
  "max_steps": 216,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.7766946372870676e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "seed": 23
  }
}