nli-MiniLM2-L6-H768-disaster-tweet-jailbreaking-augmented
This model is a fine-tuned version of cross-encoder/nli-MiniLM2-L6-H768 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2165
- Accuracy: 0.9661
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 |
|---|---|---|---|---|
| 0.5576 | 1.0 | 1680 | 0.5986 | 0.7131 |
| 0.3919 | 2.0 | 3360 | 0.4311 | 0.8190 |
| 0.6185 | 3.0 | 5040 | 0.3797 | 0.8979 |
| 0.1309 | 4.0 | 6720 | 0.3437 | 0.9110 |
| 0.0780 | 5.0 | 8400 | 0.3151 | 0.9381 |
| 0.0110 | 6.0 | 10080 | 0.2230 | 0.9563 |
| 0.0162 | 7.0 | 11760 | 0.2501 | 0.9548 |
| 0.0014 | 8.0 | 13440 | 0.2171 | 0.9664 |
| 0.0005 | 9.0 | 15120 | 0.2393 | 0.9643 |
| 0.0036 | 10.0 | 16800 | 0.2299 | 0.9664 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2