<!-- 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_40KGen_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: 0.0202
- Accuracy: 0.9974
- F1: 0.9722
- Precision: 0.9989
- Recall: 0.9468
- Roc Auc Score: 0.9734
- Tpr At Fpr 0.01: 0.9538
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0187 | 1.0 | 91875 | 0.0418 | 0.9936 | 0.9283 | 0.9968 | 0.8686 | 0.9342 | 0.8558 |
| 0.0035 | 2.0 | 183750 | 0.0279 | 0.9954 | 0.9488 | 0.9991 | 0.9034 | 0.9517 | 0.9336 |
| 0.0021 | 3.0 | 275625 | 0.0237 | 0.9971 | 0.9688 | 0.9979 | 0.9414 | 0.9707 | 0.9384 |
| 0.0021 | 4.0 | 367500 | 0.0202 | 0.9973 | 0.9713 | 0.9985 | 0.9456 | 0.9728 | 0.9532 |
| 0.0003 | 5.0 | 459375 | 0.0202 | 0.9974 | 0.9722 | 0.9989 | 0.9468 | 0.9734 | 0.9538 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
