Onlyphish_100KP_BFall_fromB_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: 0.0215
- Accuracy: 0.9974
- F1: 0.9724
- Precision: 0.9989
- Recall: 0.9472
- Roc Auc Score: 0.9736
- Tpr At Fpr 0.01: 0.9548
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 |
---|---|---|---|---|---|---|---|---|---|
0.0021 | 1.0 | 72188 | 0.0346 | 0.995 | 0.9449 | 0.9943 | 0.9002 | 0.9500 | 0.8748 |
0.0025 | 2.0 | 144376 | 0.0316 | 0.9959 | 0.9547 | 0.9989 | 0.9142 | 0.9571 | 0.9218 |
0.0019 | 3.0 | 216564 | 0.0289 | 0.9960 | 0.9566 | 0.9996 | 0.9172 | 0.9586 | 0.9382 |
0.0013 | 4.0 | 288752 | 0.0193 | 0.9975 | 0.9727 | 0.9985 | 0.9482 | 0.9741 | 0.9494 |
0.001 | 5.0 | 360940 | 0.0215 | 0.9974 | 0.9724 | 0.9989 | 0.9472 | 0.9736 | 0.9548 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 14