run-2/checkpoint-208/trainer_state.json

{
  "best_metric": 0.9808268424206111,
  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-105",
  "epoch": 3.961904761904762,
  "eval_steps": 500,
  "global_step": 208,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.99,
      "eval_accuracy": 0.9720191731575794,
      "eval_loss": 0.08049887418746948,
      "eval_runtime": 129.4849,
      "eval_samples_per_second": 128.895,
      "eval_steps_per_second": 16.118,
      "step": 52
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9808268424206111,
      "eval_loss": 0.0663532018661499,
      "eval_runtime": 129.584,
      "eval_samples_per_second": 128.797,
      "eval_steps_per_second": 16.105,
      "step": 105
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.9679448771719592,
      "eval_loss": 0.11977529525756836,
      "eval_runtime": 129.6054,
      "eval_samples_per_second": 128.776,
      "eval_steps_per_second": 16.103,
      "step": 157
    },
    {
      "epoch": 3.96,
      "eval_accuracy": 0.9803475134811265,
      "eval_loss": 0.07485608756542206,
      "eval_runtime": 129.6725,
      "eval_samples_per_second": 128.709,
      "eval_steps_per_second": 16.094,
      "step": 208
    }
  ],
  "logging_steps": 500,
  "max_steps": 208,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.848744961833747e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 32,
    "seed": 40
  }
}