BERT_QandA
This model is a fine-tuned version of bert-base-uncased on the circa dataset. It achieves the following results on the evaluation set:
- Loss: 0.4298
- Accuracy: 0.8765
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5797 | 1.0 | 619 | 0.4172 | 0.8532 |
| 0.3531 | 2.0 | 1238 | 0.3885 | 0.8735 |
| 0.2334 | 3.0 | 1857 | 0.4298 | 0.8765 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0.dev20230220
- Datasets 2.10.0
- Tokenizers 0.11.0