<!-- 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_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_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0226
- Accuracy: 0.9980
- F1: 0.9781
- Precision: 0.9973
- Recall: 0.9596
- Roc Auc Score: 0.9797
- Tpr At Fpr 0.01: 0.9532
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.01 | 1.0 | 21554 | 0.0173 | 0.9967 | 0.9641 | 0.9976 | 0.9328 | 0.9663 | 0.9318 |
| 0.0053 | 2.0 | 43108 | 0.0112 | 0.9979 | 0.9774 | 0.9899 | 0.9652 | 0.9824 | 0.9164 |
| 0.0021 | 3.0 | 64662 | 0.0166 | 0.9977 | 0.9750 | 0.9960 | 0.9548 | 0.9773 | 0.9256 |
| 0.0 | 4.0 | 86216 | 0.0180 | 0.9979 | 0.9776 | 0.9963 | 0.9596 | 0.9797 | 0.951 |
| 0.0 | 5.0 | 107770 | 0.0226 | 0.9980 | 0.9781 | 0.9973 | 0.9596 | 0.9797 | 0.9532 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
