<!-- 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_subdomain_100KP_BFall_fromP_95K_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_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0449
- Accuracy: 0.9977
- F1: 0.9757
- Precision: 0.9990
- Recall: 0.9536
- Roc Auc Score: 0.9768
- Tpr At Fpr 0.01: 0.96
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0184 | 1.0 | 18282 | 0.0527 | 0.9965 | 0.9618 | 0.9978 | 0.9282 | 0.9641 | 0.9278 |
| 0.0092 | 2.0 | 36564 | 0.0574 | 0.9966 | 0.9625 | 0.9981 | 0.9294 | 0.9647 | 0.9342 |
| 0.0052 | 3.0 | 54846 | 0.0422 | 0.9974 | 0.9722 | 0.9987 | 0.947 | 0.9735 | 0.9532 |
| 0.0013 | 4.0 | 73128 | 0.0404 | 0.9979 | 0.9771 | 0.9981 | 0.957 | 0.9785 | 0.9576 |
| 0.0006 | 5.0 | 91410 | 0.0449 | 0.9977 | 0.9757 | 0.9990 | 0.9536 | 0.9768 | 0.96 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
