<!-- 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_fromP_10KGen_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: 0.0209
- Accuracy: 0.9965
- F1: 0.9619
- Precision: 0.9996
- Recall: 0.927
- Roc Auc Score: 0.9635
- Tpr At Fpr 0.01: 0.9434
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0085 | 1.0 | 72188 | 0.0459 | 0.9920 | 0.9096 | 0.9860 | 0.8442 | 0.9218 | 0.0 |
| 0.007 | 2.0 | 144376 | 0.0406 | 0.9939 | 0.9313 | 0.9991 | 0.8722 | 0.9361 | 0.8966 |
| 0.0017 | 3.0 | 216564 | 0.0273 | 0.9960 | 0.9561 | 0.9993 | 0.9164 | 0.9582 | 0.9216 |
| 0.0011 | 4.0 | 288752 | 0.0221 | 0.9969 | 0.9666 | 0.9985 | 0.9366 | 0.9683 | 0.938 |
| 0.0016 | 5.0 | 360940 | 0.0209 | 0.9965 | 0.9619 | 0.9996 | 0.927 | 0.9635 | 0.9434 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
