<!-- 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. -->
Baseline_100Kphish_benignFall_5_20_20
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_MixGPT2_using_benign_200K_top_p_0.75 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0216
- Accuracy: 0.9976
- F1: 0.9745
- Precision: 0.9989
- Recall: 0.9512
- Roc Auc Score: 0.9756
- Tpr At Fpr 0.01: 0.9544
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0079 | 1.0 | 18750 | 0.0117 | 0.9976 | 0.9749 | 0.9923 | 0.958 | 0.9788 | 0.876 |
| 0.0057 | 2.0 | 37500 | 0.0255 | 0.9955 | 0.9509 | 0.9987 | 0.9074 | 0.9537 | 0.926 |
| 0.0025 | 3.0 | 56250 | 0.0166 | 0.9976 | 0.9748 | 0.9967 | 0.9538 | 0.9768 | 0.948 |
| 0.0016 | 4.0 | 75000 | 0.0187 | 0.9978 | 0.9765 | 0.9956 | 0.958 | 0.9789 | 0.9468 |
| 0.0008 | 5.0 | 93750 | 0.0216 | 0.9976 | 0.9745 | 0.9989 | 0.9512 | 0.9756 | 0.9544 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
