library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics: - accuracy
model-index: - name: bert-base-uncased-trustairlab-jailbreak
results: []
bert-base-uncased-trustairlab-jailbreak
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1821
- Accuracy: 0.9404
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 |
|---|---|---|---|---|
| 0.2661 | 1.0 | 605 | 0.2187 | 0.9400 |
| 0.1229 | 2.0 | 1210 | 0.1819 | 0.9400 |
| 0.2125 | 3.0 | 1815 | 0.2003 | 0.9417 |
| 0.1114 | 4.0 | 2420 | 0.2431 | 0.9425 |
| 0.0508 | 5.0 | 3025 | 0.3173 | 0.9379 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2