wav2vec2-jailbreak-classification_new
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0627
- Accuracy: 1.0
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.562 | 1.0 | 31 | 0.4704 | 0.9693 |
| 0.2247 | 2.0 | 62 | 0.1643 | 0.9959 |
| 0.0949 | 3.0 | 93 | 0.0689 | 0.9980 |
| 0.0591 | 4.0 | 124 | 0.0476 | 0.9959 |
| 0.0381 | 5.0 | 155 | 0.0331 | 0.9980 |
| 0.0333 | 6.0 | 186 | 0.0314 | 0.9980 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2