<!-- 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_10KGen_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: 0.0557
- Accuracy: 0.9950
- F1: 0.9452
- Precision: 0.9960
- Recall: 0.8994
- Roc Auc Score: 0.9496
- Tpr At Fpr 0.01: 0.8826
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0118 | 1.0 | 6875 | 0.0270 | 0.9930 | 0.9214 | 0.9947 | 0.8582 | 0.9290 | 0.8176 |
| 0.0063 | 2.0 | 13750 | 0.0301 | 0.9944 | 0.9383 | 0.9957 | 0.8872 | 0.9435 | 0.855 |
| 0.0023 | 3.0 | 20625 | 0.0342 | 0.9951 | 0.9468 | 0.9900 | 0.9072 | 0.9534 | 0.8402 |
| 0.0 | 4.0 | 27500 | 0.0426 | 0.9954 | 0.9500 | 0.9937 | 0.91 | 0.9549 | 0.8686 |
| 0.0 | 5.0 | 34375 | 0.0557 | 0.9950 | 0.9452 | 0.9960 | 0.8994 | 0.9496 | 0.8826 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
