bert-base-uncased-disaster-tweet-jailbreaking-augmented
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1527
- Accuracy: 0.9798
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4677 | 1.0 | 1680 | 0.5091 | 0.7702 |
| 0.4860 | 2.0 | 3360 | 0.3487 | 0.9039 |
| 0.3700 | 3.0 | 5040 | 0.3000 | 0.9411 |
| 0.0304 | 4.0 | 6720 | 0.1937 | 0.9610 |
| 0.0713 | 5.0 | 8400 | 0.1989 | 0.9670 |
| 0.0002 | 6.0 | 10080 | 0.2061 | 0.9685 |
| 0.0001 | 7.0 | 11760 | 0.1681 | 0.9729 |
| 0.0001 | 8.0 | 13440 | 0.1818 | 0.975 |
| 0.0000 | 9.0 | 15120 | 0.1528 | 0.9798 |
| 0.0000 | 10.0 | 16800 | 0.1581 | 0.9795 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2