<!-- 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_domain_100KP_BFall_fromP_90K_topP_0.75_ratio2.63
This model is a fine-tuned version of bert-base-uncased on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_Benign10MGPT2_using_phish_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0248
- Accuracy: 0.9971
- F1: 0.9693
- Precision: 0.9939
- Recall: 0.9458
- Roc Auc Score: 0.9728
- Tpr At Fpr 0.01: 0.9312
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0153 | 1.0 | 21554 | 0.0251 | 0.9950 | 0.9443 | 0.9980 | 0.896 | 0.9480 | 0.8982 |
| 0.0084 | 2.0 | 43108 | 0.0175 | 0.9970 | 0.9675 | 0.9914 | 0.9448 | 0.9722 | 0.9184 |
| 0.0041 | 3.0 | 64662 | 0.0135 | 0.9975 | 0.9737 | 0.9873 | 0.9606 | 0.9800 | 0.904 |
| 0.0013 | 4.0 | 86216 | 0.0210 | 0.9969 | 0.9668 | 0.9922 | 0.9426 | 0.9711 | 0.9174 |
| 0.0015 | 5.0 | 107770 | 0.0248 | 0.9971 | 0.9693 | 0.9939 | 0.9458 | 0.9728 | 0.9312 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
