<!-- 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_suffix_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_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0285
- Accuracy: 0.9965
- F1: 0.9628
- Precision: 0.9801
- Recall: 0.946
- Roc Auc Score: 0.9725
- Tpr At Fpr 0.01: 0.8598
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0215 | 1.0 | 21554 | 0.0216 | 0.9947 | 0.9442 | 0.9449 | 0.9434 | 0.9703 | 0.825 |
| 0.0114 | 2.0 | 43108 | 0.0157 | 0.9963 | 0.9605 | 0.9649 | 0.9562 | 0.9772 | 0.8046 |
| 0.0059 | 3.0 | 64662 | 0.0234 | 0.9960 | 0.9569 | 0.9773 | 0.9374 | 0.9682 | 0.8252 |
| 0.0028 | 4.0 | 86216 | 0.0269 | 0.9962 | 0.9599 | 0.9708 | 0.9492 | 0.9739 | 0.8512 |
| 0.0006 | 5.0 | 107770 | 0.0285 | 0.9965 | 0.9628 | 0.9801 | 0.946 | 0.9725 | 0.8598 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
