<!-- 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. -->
OnlyPhishGPT2_Suffix_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_OnlyPhishGPT2_using_phish_95K_top_p_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0241
- Accuracy: 0.9975
- F1: 0.9726
- Precision: 0.9992
- Recall: 0.9474
- Roc Auc Score: 0.9737
- Tpr At Fpr 0.01: 0.9552
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0047 | 1.0 | 35625 | 0.0152 | 0.9974 | 0.9721 | 0.9960 | 0.9494 | 0.9746 | 0.9272 |
| 0.0022 | 2.0 | 71250 | 0.0167 | 0.9974 | 0.9723 | 0.9964 | 0.9494 | 0.9746 | 0.9304 |
| 0.0019 | 3.0 | 106875 | 0.0273 | 0.9968 | 0.9651 | 0.9989 | 0.9334 | 0.9667 | 0.9406 |
| 0.0001 | 4.0 | 142500 | 0.0267 | 0.9975 | 0.9728 | 0.9983 | 0.9486 | 0.9743 | 0.9504 |
| 0.0 | 5.0 | 178125 | 0.0241 | 0.9975 | 0.9726 | 0.9992 | 0.9474 | 0.9737 | 0.9552 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
