run-7/checkpoint-536/trainer_state.json

{
  "best_metric": 0.4971074930428892,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-536",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.4807068407535553,
      "eval_matthews_correlation": 0.44251427534495513,
      "eval_runtime": 2.9285,
      "eval_samples_per_second": 356.153,
      "eval_steps_per_second": 22.537,
      "step": 268
    },
    {
      "epoch": 1.8656716417910446,
      "grad_norm": 7.641021251678467,
      "learning_rate": 7.161909082579098e-06,
      "loss": 0.4547,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.47382214665412903,
      "eval_matthews_correlation": 0.4971074930428892,
      "eval_runtime": 2.8647,
      "eval_samples_per_second": 364.081,
      "eval_steps_per_second": 23.039,
      "step": 536
    }
  ],
  "logging_steps": 500,
  "max_steps": 804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 154401102149088.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.8941364810505247e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 32,
    "seed": 9
  }
}