<!-- 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. -->
Onlyphish_100KP_BFall_fromB_30KGen_topP_0.75
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: 0.0188
- Accuracy: 0.9973
- F1: 0.9707
- Precision: 0.9996
- Recall: 0.9434
- Roc Auc Score: 0.9717
- Tpr At Fpr 0.01: 0.9624
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0022 | 1.0 | 85313 | 0.0263 | 0.9963 | 0.9599 | 0.9938 | 0.9282 | 0.9640 | 0.8954 |
| 0.0032 | 2.0 | 170626 | 0.0296 | 0.9954 | 0.9490 | 0.9987 | 0.904 | 0.9520 | 0.925 |
| 0.0042 | 3.0 | 255939 | 0.0226 | 0.9971 | 0.9683 | 0.9985 | 0.9398 | 0.9699 | 0.946 |
| 0.001 | 4.0 | 341252 | 0.0187 | 0.9973 | 0.9708 | 0.9996 | 0.9436 | 0.9718 | 0.957 |
| 0.0 | 5.0 | 426565 | 0.0188 | 0.9973 | 0.9707 | 0.9996 | 0.9434 | 0.9717 | 0.9624 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
