run-3/checkpoint-42/trainer_state.json

{
  "best_metric": 0.006558425391695436,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-14",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.7035912871360779,
      "eval_matthews_correlation": 0.006558425391695436,
      "eval_runtime": 0.7409,
      "eval_samples_per_second": 1407.711,
      "eval_steps_per_second": 89.079,
      "step": 14
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6941744089126587,
      "eval_matthews_correlation": -0.036114649977135045,
      "eval_runtime": 0.8152,
      "eval_samples_per_second": 1279.437,
      "eval_steps_per_second": 80.962,
      "step": 28
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.687230110168457,
      "eval_matthews_correlation": -0.00313313961007992,
      "eval_runtime": 0.8165,
      "eval_samples_per_second": 1277.436,
      "eval_steps_per_second": 80.835,
      "step": 42
    }
  ],
  "logging_steps": 500,
  "max_steps": 70,
  "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": 1.1291452758992565e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 64,
    "seed": 34
  }
}