<!-- 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_50Kphish_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: 0.0294
- Accuracy: 0.9959
- F1: 0.9549
- Precision: 0.9996
- Recall: 0.914
- Roc Auc Score: 0.9570
- Tpr At Fpr 0.01: 0.932
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0089 | 1.0 | 32813 | 0.0386 | 0.9944 | 0.9379 | 0.9957 | 0.8864 | 0.9431 | 0.8642 |
| 0.008 | 2.0 | 65626 | 0.0524 | 0.9917 | 0.9046 | 0.9995 | 0.8262 | 0.9131 | 0.8586 |
| 0.0027 | 3.0 | 98439 | 0.0265 | 0.9965 | 0.9624 | 0.9961 | 0.9308 | 0.9653 | 0.919 |
| 0.0013 | 4.0 | 131252 | 0.0302 | 0.9962 | 0.9585 | 0.9989 | 0.9212 | 0.9606 | 0.9236 |
| 0.0006 | 5.0 | 164065 | 0.0294 | 0.9959 | 0.9549 | 0.9996 | 0.914 | 0.9570 | 0.932 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
