electra-base-discriminator-trustairlab-jailbreak
This model is a fine-tuned version of google/electra-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1880
- Accuracy: 0.9417
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.2914 | 1.0 | 605 | 0.2225 | 0.9355 |
| 0.1846 | 2.0 | 1210 | 0.1878 | 0.9375 |
| 0.2480 | 3.0 | 1815 | 0.2106 | 0.9375 |
| 0.1651 | 4.0 | 2420 | 0.1874 | 0.9417 |
| 0.1016 | 5.0 | 3025 | 0.2330 | 0.9392 |
| 0.0392 | 6.0 | 3630 | 0.2553 | 0.9433 |
| 0.1095 | 7.0 | 4235 | 0.2747 | 0.9404 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2