<!-- 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. -->
MixGPT2V2_domain_100KP_BFall_fromB_90K_topP_0.75_ratio5
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_MixGPT2V2_using_benign_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0432
- Accuracy: 0.9977
- F1: 0.9757
- Precision: 0.9948
- Recall: 0.9574
- Roc Auc Score: 0.9786
- Tpr At Fpr 0.01: 0.934
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0432 | 1.0 | 17813 | 0.0393 | 0.9972 | 0.9701 | 0.9802 | 0.9602 | 0.9796 | 0.8248 |
| 0.0232 | 2.0 | 35626 | 0.0362 | 0.9975 | 0.9728 | 0.9944 | 0.9522 | 0.9760 | 0.9352 |
| 0.008 | 3.0 | 53439 | 0.0459 | 0.9972 | 0.9706 | 0.9880 | 0.9538 | 0.9766 | 0.9168 |
| 0.0047 | 4.0 | 71252 | 0.0442 | 0.9975 | 0.9728 | 0.9939 | 0.9526 | 0.9762 | 0.9314 |
| 0.0026 | 5.0 | 89065 | 0.0432 | 0.9977 | 0.9757 | 0.9948 | 0.9574 | 0.9786 | 0.934 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
