<!-- 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. -->
Onlyphish_100KP_BFall_fromB_10KGen_topP_0.75_noaddedB
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_OnlyPhishGPT2_using_benign_40K_top_p_0.75 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0191
- Accuracy: 0.9973
- F1: 0.9705
- Precision: 0.9989
- Recall: 0.9436
- Roc Auc Score: 0.9718
- Tpr At Fpr 0.01: 0.9566
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0034 | 1.0 | 65938 | 0.0158 | 0.9972 | 0.9704 | 0.9912 | 0.9504 | 0.9750 | 0.0336 |
| 0.0028 | 2.0 | 131876 | 0.0288 | 0.9967 | 0.9641 | 0.9994 | 0.9312 | 0.9656 | 0.9374 |
| 0.002 | 3.0 | 197814 | 0.0186 | 0.9965 | 0.9616 | 0.9989 | 0.927 | 0.9635 | 0.942 |
| 0.0008 | 4.0 | 263752 | 0.0232 | 0.9970 | 0.9676 | 0.9989 | 0.9382 | 0.9691 | 0.9508 |
| 0.0002 | 5.0 | 329690 | 0.0191 | 0.9973 | 0.9705 | 0.9989 | 0.9436 | 0.9718 | 0.9566 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
