<!-- 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_subdomain_100KP_BFall_fromB_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_benign_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0946
- Accuracy: 0.9828
- F1: 0.8397
- Precision: 0.7543
- Recall: 0.9468
- Roc Auc Score: 0.9657
- Tpr At Fpr 0.01: 0.6862
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.1228 | 1.0 | 21554 | 0.0707 | 0.9788 | 0.8034 | 0.7181 | 0.9116 | 0.9469 | 0.7204 |
| 0.0973 | 2.0 | 43108 | 0.0724 | 0.9788 | 0.8110 | 0.7040 | 0.9562 | 0.9680 | 0.7214 |
| 0.0712 | 3.0 | 64662 | 0.0680 | 0.9828 | 0.8389 | 0.7576 | 0.9396 | 0.9623 | 0.6868 |
| 0.055 | 4.0 | 86216 | 0.0691 | 0.9847 | 0.8548 | 0.7804 | 0.9448 | 0.9658 | 0.7404 |
| 0.0297 | 5.0 | 107770 | 0.0946 | 0.9828 | 0.8397 | 0.7543 | 0.9468 | 0.9657 | 0.6862 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
