<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Benign10MGPT2_fromP_BFall_40KGen_toP_0.75
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0969
- Accuracy: 0.9891
- F1: 0.8714
- Precision: 0.9941
- Recall: 0.7756
- Roc Auc Score: 0.8877
- Tpr At Fpr 0.01: 0.7466
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0125 | 1.0 | 32813 | 0.0595 | 0.9879 | 0.8582 | 0.9722 | 0.7682 | 0.8836 | 0.4626 |
| 0.0073 | 2.0 | 65626 | 0.0586 | 0.9881 | 0.8574 | 0.9934 | 0.7542 | 0.8770 | 0.7238 |
| 0.0057 | 3.0 | 98439 | 0.0760 | 0.987 | 0.8426 | 0.9948 | 0.7308 | 0.8653 | 0.7106 |
| 0.0028 | 4.0 | 131252 | 0.0734 | 0.9896 | 0.8778 | 0.9937 | 0.7862 | 0.8930 | 0.7676 |
| 0.0013 | 5.0 | 164065 | 0.0969 | 0.9891 | 0.8714 | 0.9941 | 0.7756 | 0.8877 | 0.7466 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
