<!-- 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_Suffix_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_OnlyPhishGPT2_using_phish_95K_top_p_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0213
- Accuracy: 0.9976
- F1: 0.9742
- Precision: 0.9981
- Recall: 0.9514
- Roc Auc Score: 0.9757
- Tpr At Fpr 0.01: 0.9528
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0064 | 1.0 | 21554 | 0.0135 | 0.9969 | 0.9667 | 0.9932 | 0.9416 | 0.9706 | 0.9054 |
| 0.0052 | 2.0 | 43108 | 0.0130 | 0.9977 | 0.9759 | 0.9875 | 0.9646 | 0.9820 | 0.8418 |
| 0.0015 | 3.0 | 64662 | 0.0193 | 0.9971 | 0.9685 | 0.9977 | 0.941 | 0.9704 | 0.9368 |
| 0.0006 | 4.0 | 86216 | 0.0184 | 0.9979 | 0.9780 | 0.9975 | 0.9592 | 0.9795 | 0.9556 |
| 0.0017 | 5.0 | 107770 | 0.0213 | 0.9976 | 0.9742 | 0.9981 | 0.9514 | 0.9757 | 0.9528 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
