electra-base-discriminator-disaster-tweet-jailbreaking-augmented
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: 0.1216
- Accuracy: 0.9789
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 |
|---|---|---|---|---|
| 0.5639 | 1.0 | 1680 | 0.5448 | 0.7354 |
| 0.4988 | 2.0 | 3360 | 0.4278 | 0.8402 |
| 0.3380 | 3.0 | 5040 | 0.3659 | 0.9060 |
| 0.1394 | 4.0 | 6720 | 0.2064 | 0.9512 |
| 0.1381 | 5.0 | 8400 | 0.1748 | 0.9661 |
| 0.0839 | 6.0 | 10080 | 0.1414 | 0.9747 |
| 0.0015 | 7.0 | 11760 | 0.1214 | 0.9789 |
| 0.0007 | 8.0 | 13440 | 0.1433 | 0.9768 |
| 0.0002 | 9.0 | 15120 | 0.1347 | 0.9780 |
| 0.0002 | 10.0 | 16800 | 0.1340 | 0.9789 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2