roberta-base-disaster-tweet-jailbreaking-augmented
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1776
- Accuracy: 0.9717
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 |
|---|---|---|---|---|
| 0.6028 | 1.0 | 1680 | 0.5656 | 0.7125 |
| 0.4653 | 2.0 | 3360 | 0.4785 | 0.8196 |
| 0.4870 | 3.0 | 5040 | 0.3783 | 0.8982 |
| 0.0446 | 4.0 | 6720 | 0.3292 | 0.9318 |
| 0.1025 | 5.0 | 8400 | 0.2381 | 0.9565 |
| 0.0945 | 6.0 | 10080 | 0.2062 | 0.9670 |
| 0.0005 | 7.0 | 11760 | 0.1778 | 0.9717 |
| 0.0009 | 8.0 | 13440 | 0.1945 | 0.9723 |
| 0.0002 | 9.0 | 15120 | 0.1848 | 0.9759 |
| 0.0001 | 10.0 | 16800 | 0.1804 | 0.9765 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2