<!-- 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_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_MixGPT2V2_using_benign_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0212
- Accuracy: 0.9975
- F1: 0.9729
- Precision: 0.9903
- Recall: 0.9562
- Roc Auc Score: 0.9779
- Tpr At Fpr 0.01: 0.8508
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0155 | 1.0 | 21554 | 0.0174 | 0.9957 | 0.9548 | 0.9576 | 0.952 | 0.9749 | 0.8056 |
| 0.006 | 2.0 | 43108 | 0.0163 | 0.9962 | 0.9603 | 0.9499 | 0.971 | 0.9842 | 0.7598 |
| 0.0037 | 3.0 | 64662 | 0.0184 | 0.9968 | 0.9660 | 0.9856 | 0.9472 | 0.9733 | 0.8876 |
| 0.0014 | 4.0 | 86216 | 0.0205 | 0.9972 | 0.9700 | 0.9784 | 0.9618 | 0.9804 | 0.7864 |
| 0.0 | 5.0 | 107770 | 0.0212 | 0.9975 | 0.9729 | 0.9903 | 0.9562 | 0.9779 | 0.8508 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
