<!-- 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_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_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0281
- Accuracy: 0.9968
- F1: 0.9657
- Precision: 0.9808
- Recall: 0.951
- Roc Auc Score: 0.9750
- Tpr At Fpr 0.01: 0.8582
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0252 | 1.0 | 21554 | 0.0191 | 0.9956 | 0.9519 | 0.9807 | 0.9248 | 0.9619 | 0.855 |
| 0.0152 | 2.0 | 43108 | 0.0160 | 0.9961 | 0.9596 | 0.9578 | 0.9614 | 0.9796 | 0.8712 |
| 0.0098 | 3.0 | 64662 | 0.0173 | 0.9963 | 0.9609 | 0.9699 | 0.9522 | 0.9754 | 0.846 |
| 0.004 | 4.0 | 86216 | 0.0213 | 0.9969 | 0.9671 | 0.9777 | 0.9568 | 0.9779 | 0.8478 |
| 0.0007 | 5.0 | 107770 | 0.0281 | 0.9968 | 0.9657 | 0.9808 | 0.951 | 0.9750 | 0.8582 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
