<!-- 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_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_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0431
- Accuracy: 0.9977
- F1: 0.9757
- Precision: 0.9983
- Recall: 0.954
- Roc Auc Score: 0.9770
- Tpr At Fpr 0.01: 0.951
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0257 | 1.0 | 10777 | 0.0346 | 0.9975 | 0.9735 | 0.9887 | 0.9588 | 0.9791 | 0.9196 |
| 0.0155 | 2.0 | 21554 | 0.0306 | 0.9979 | 0.9774 | 0.9942 | 0.9612 | 0.9805 | 0.9478 |
| 0.0053 | 3.0 | 32331 | 0.0286 | 0.9982 | 0.9806 | 0.9949 | 0.9668 | 0.9833 | 0.955 |
| 0.0035 | 4.0 | 43108 | 0.0354 | 0.9980 | 0.9784 | 0.9967 | 0.9608 | 0.9803 | 0.9564 |
| 0.001 | 5.0 | 53885 | 0.0431 | 0.9977 | 0.9757 | 0.9983 | 0.954 | 0.9770 | 0.951 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
