bert-base-uncased-finetuned-swag
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8045
- Accuracy: 0.7616
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7901 | 1.0 | 4597 | 0.6447 | 0.7491 |
| 0.4732 | 2.0 | 9194 | 0.6830 | 0.7549 |
| 0.2773 | 3.0 | 13791 | 0.8404 | 0.7523 |
| 0.2032 | 4.0 | 18388 | 1.2185 | 0.7466 |
| 0.1395 | 5.0 | 22985 | 1.6044 | 0.7513 |
| 0.1034 | 6.0 | 27582 | 2.0941 | 0.7520 |
| 0.0584 | 7.0 | 32179 | 2.5468 | 0.7528 |
| 0.0412 | 8.0 | 36776 | 2.5621 | 0.7562 |
| 0.0163 | 9.0 | 41373 | 2.7435 | 0.7604 |
| 0.0094 | 10.0 | 45970 | 2.8045 | 0.7616 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.7.0+gitf717b2a
- Datasets 3.6.0
- Tokenizers 0.21.4