<!-- 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_30KGen_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: 0.0981
- Accuracy: 0.9876
- F1: 0.8504
- Precision: 0.9938
- Recall: 0.7432
- Roc Auc Score: 0.8715
- Tpr At Fpr 0.01: 0.6914
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0097 | 1.0 | 26250 | 0.0808 | 0.9840 | 0.8004 | 0.9874 | 0.673 | 0.8363 | 0.6018 |
| 0.011 | 2.0 | 52500 | 0.0652 | 0.9867 | 0.8389 | 0.9881 | 0.7288 | 0.8642 | 0.6536 |
| 0.0025 | 3.0 | 78750 | 0.0730 | 0.9868 | 0.8401 | 0.9889 | 0.7302 | 0.8649 | 0.649 |
| 0.0023 | 4.0 | 105000 | 0.1064 | 0.9866 | 0.8367 | 0.9937 | 0.7226 | 0.8612 | 0.6878 |
| 0.0011 | 5.0 | 131250 | 0.0981 | 0.9876 | 0.8504 | 0.9938 | 0.7432 | 0.8715 | 0.6914 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
