<!-- 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_95K_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: 0.0286
- Accuracy: 0.9964
- F1: 0.9612
- Precision: 0.9728
- Recall: 0.95
- Roc Auc Score: 0.9743
- Tpr At Fpr 0.01: 0.7924
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0218 | 1.0 | 22121 | 0.0193 | 0.9952 | 0.9485 | 0.9717 | 0.9264 | 0.9625 | 0.7698 |
| 0.013 | 2.0 | 44242 | 0.0213 | 0.9957 | 0.9546 | 0.9675 | 0.942 | 0.9702 | 0.799 |
| 0.0041 | 3.0 | 66363 | 0.0262 | 0.9951 | 0.9494 | 0.9395 | 0.9596 | 0.9783 | 0.792 |
| 0.0034 | 4.0 | 88484 | 0.0223 | 0.9964 | 0.9618 | 0.9657 | 0.958 | 0.9781 | 0.8558 |
| 0.001 | 5.0 | 110605 | 0.0286 | 0.9964 | 0.9612 | 0.9728 | 0.95 | 0.9743 | 0.7924 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
