<!-- 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_20KGen_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: 0.1101
- Accuracy: 0.9888
- F1: 0.8669
- Precision: 0.9948
- Recall: 0.7682
- Roc Auc Score: 0.884
- Tpr At Fpr 0.01: 0.7442
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0105 | 1.0 | 19688 | 0.0686 | 0.9851 | 0.8158 | 0.9957 | 0.691 | 0.8454 | 0.654 |
| 0.0069 | 2.0 | 39376 | 0.0458 | 0.9901 | 0.8866 | 0.9794 | 0.8098 | 0.9045 | 0.679 |
| 0.0051 | 3.0 | 59064 | 0.0698 | 0.9903 | 0.8874 | 0.9901 | 0.804 | 0.9018 | 0.747 |
| 0.0013 | 4.0 | 78752 | 0.0980 | 0.9893 | 0.8737 | 0.9949 | 0.7788 | 0.8893 | 0.7374 |
| 0.0007 | 5.0 | 98440 | 0.1101 | 0.9888 | 0.8669 | 0.9948 | 0.7682 | 0.884 | 0.7442 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
