<!-- 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_10K_fromB_BFall_30KGen_topP_0.75_noaddedB
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: 0.0506
- Accuracy: 0.9949
- F1: 0.9434
- Precision: 0.9975
- Recall: 0.8948
- Roc Auc Score: 0.9473
- Tpr At Fpr 0.01: 0.8848
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0119 | 1.0 | 7500 | 0.0230 | 0.9947 | 0.9423 | 0.9869 | 0.9016 | 0.9505 | 0.7658 |
| 0.0067 | 2.0 | 15000 | 0.0320 | 0.9950 | 0.9447 | 0.9958 | 0.8986 | 0.9492 | 0.8786 |
| 0.0013 | 3.0 | 22500 | 0.0353 | 0.9953 | 0.9480 | 0.9945 | 0.9056 | 0.9527 | 0.8772 |
| 0.0007 | 4.0 | 30000 | 0.0373 | 0.9955 | 0.9509 | 0.9939 | 0.9114 | 0.9556 | 0.8862 |
| 0.0 | 5.0 | 37500 | 0.0506 | 0.9949 | 0.9434 | 0.9975 | 0.8948 | 0.9473 | 0.8848 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
