run-0/checkpoint-28/trainer_state.json

{
  "best_metric": 0.278777673546003,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-28",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 28,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.6069979667663574,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 1.5899,
      "eval_samples_per_second": 656.018,
      "eval_steps_per_second": 82.395,
      "step": 7
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5834578275680542,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 2.4953,
      "eval_samples_per_second": 417.989,
      "eval_steps_per_second": 52.499,
      "step": 14
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5535554885864258,
      "eval_matthews_correlation": 0.20447908125390313,
      "eval_runtime": 1.2012,
      "eval_samples_per_second": 868.263,
      "eval_steps_per_second": 109.053,
      "step": 21
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5610475540161133,
      "eval_matthews_correlation": 0.278777673546003,
      "eval_runtime": 1.2979,
      "eval_samples_per_second": 803.636,
      "eval_steps_per_second": 100.936,
      "step": 28
    }
  ],
  "logging_steps": 500,
  "max_steps": 28,
  "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": 6.924004119404506e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 64,
    "seed": 17
  }
}