<!-- 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. -->
Baseline_20Kphish_benignFall_20_20_20
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: 0.0540
- Accuracy: 0.9952
- F1: 0.9467
- Precision: 0.9984
- Recall: 0.9
- Roc Auc Score: 0.9500
- Tpr At Fpr 0.01: 0.9032
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0065 | 1.0 | 13125 | 0.0309 | 0.991 | 0.8959 | 0.9975 | 0.813 | 0.9064 | 0.7808 |
| 0.004 | 2.0 | 26250 | 0.0448 | 0.9926 | 0.9153 | 0.9988 | 0.8446 | 0.9223 | 0.8598 |
| 0.0019 | 3.0 | 39375 | 0.0501 | 0.9938 | 0.9302 | 0.9986 | 0.8706 | 0.9353 | 0.8818 |
| 0.0013 | 4.0 | 52500 | 0.0462 | 0.9954 | 0.9496 | 0.9967 | 0.9068 | 0.9533 | 0.895 |
| 0.0 | 5.0 | 65625 | 0.0540 | 0.9952 | 0.9467 | 0.9984 | 0.9 | 0.9500 | 0.9032 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
