<!-- 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_benignWinter_20_20_20
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0187
- Accuracy: 0.9973
- F1: 0.9705
- Precision: 0.9996
- Recall: 0.943
- Roc Auc Score: 0.9715
- Tpr At Fpr 0.01: 0.9568
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0043 | 1.0 | 65625 | 0.0343 | 0.9944 | 0.9379 | 0.9973 | 0.8852 | 0.9425 | 0.8798 |
| 0.0047 | 2.0 | 131250 | 0.0326 | 0.9951 | 0.9462 | 0.9996 | 0.8982 | 0.9491 | 0.9194 |
| 0.0027 | 3.0 | 196875 | 0.0308 | 0.9960 | 0.9559 | 0.9985 | 0.9168 | 0.9584 | 0.9276 |
| 0.0021 | 4.0 | 262500 | 0.0185 | 0.9971 | 0.9691 | 0.9996 | 0.9404 | 0.9702 | 0.9508 |
| 0.0004 | 5.0 | 328125 | 0.0187 | 0.9973 | 0.9705 | 0.9996 | 0.943 | 0.9715 | 0.9568 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
