<!-- 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. -->
Benign10MGPT2_domain_100KP_BFall_fromP_90K_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_Benign10MGPT2_using_phish_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0229
- Accuracy: 0.9976
- F1: 0.9748
- Precision: 0.9962
- Recall: 0.9542
- Roc Auc Score: 0.9770
- Tpr At Fpr 0.01: 0.9358
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.008 | 1.0 | 35625 | 0.0214 | 0.9961 | 0.9572 | 0.9983 | 0.9194 | 0.9597 | 0.9208 |
| 0.0059 | 2.0 | 71250 | 0.0239 | 0.9959 | 0.9557 | 0.9963 | 0.9182 | 0.9590 | 0.8816 |
| 0.0041 | 3.0 | 106875 | 0.0247 | 0.9968 | 0.9651 | 0.9955 | 0.9364 | 0.9681 | 0.9088 |
| 0.0001 | 4.0 | 142500 | 0.0260 | 0.9971 | 0.9687 | 0.9962 | 0.9426 | 0.9712 | 0.9298 |
| 0.0011 | 5.0 | 178125 | 0.0229 | 0.9976 | 0.9748 | 0.9962 | 0.9542 | 0.9770 | 0.9358 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
