arincon's picture
End of training
ed22e22
metadata
license: mit
base_model: roberta-base-openai-detector
tags:
  - generated_from_trainer
datasets:
  - au_tex_tification
metrics:
  - accuracy
model-index:
  - name: roberta-base-openai-detector-autextification
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: au_tex_tification
          type: au_tex_tification
          config: detection_en
          split: train
          args: detection_en
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6

roberta-base-openai-detector-autextification

This model is a fine-tuned version of roberta-base-openai-detector on the au_tex_tification dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7155
  • Accuracy: 0.6
  • Roc Auc: 0.6354

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy Roc Auc
1.0975 1.0 10 0.7345 0.65 0.5417
0.4022 2.0 20 0.6266 0.65 0.6667
0.1635 3.0 30 0.7155 0.6 0.6354

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.14.1