<!-- 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. -->
OnlyPhishGPT2_Domain_100KP_BFall_fromB_100K_topP_0.75_ratio2.5
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_100K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0200
- Accuracy: 0.9976
- F1: 0.9747
- Precision: 0.9881
- Recall: 0.9616
- Roc Auc Score: 0.9805
- Tpr At Fpr 0.01: 0.0
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0156 | 1.0 | 21875 | 0.0161 | 0.9962 | 0.9602 | 0.9710 | 0.9496 | 0.9741 | 0.836 |
| 0.0094 | 2.0 | 43750 | 0.0124 | 0.9973 | 0.9709 | 0.9884 | 0.954 | 0.9767 | 0.9 |
| 0.0042 | 3.0 | 65625 | 0.0174 | 0.9970 | 0.9678 | 0.9735 | 0.9622 | 0.9804 | 0.8922 |
| 0.0021 | 4.0 | 87500 | 0.0203 | 0.9974 | 0.9724 | 0.9836 | 0.9614 | 0.9803 | 0.0 |
| 0.0 | 5.0 | 109375 | 0.0200 | 0.9976 | 0.9747 | 0.9881 | 0.9616 | 0.9805 | 0.0 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
