<!-- 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_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_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0189
- Accuracy: 0.9980
- F1: 0.9791
- Precision: 0.9963
- Recall: 0.9626
- Roc Auc Score: 0.9812
- Tpr At Fpr 0.01: 0.9476
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0077 | 1.0 | 22121 | 0.0141 | 0.9962 | 0.9590 | 0.9957 | 0.925 | 0.9624 | 0.9076 |
| 0.0046 | 2.0 | 44242 | 0.0198 | 0.9969 | 0.9660 | 0.9977 | 0.9362 | 0.9680 | 0.9348 |
| 0.0024 | 3.0 | 66363 | 0.0203 | 0.9975 | 0.9728 | 0.9954 | 0.9512 | 0.9755 | 0.94 |
| 0.0009 | 4.0 | 88484 | 0.0181 | 0.9977 | 0.9751 | 0.9973 | 0.9538 | 0.9768 | 0.9428 |
| 0.0 | 5.0 | 110605 | 0.0189 | 0.9980 | 0.9791 | 0.9963 | 0.9626 | 0.9812 | 0.9476 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
