bert_base_train_book_qnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_train_book on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.3291
- Accuracy: 0.8561
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4629 | 1.0 | 410 | 0.3791 | 0.8351 |
| 0.3327 | 2.0 | 820 | 0.3291 | 0.8561 |
| 0.2401 | 3.0 | 1230 | 0.3389 | 0.8645 |
| 0.1563 | 4.0 | 1640 | 0.4629 | 0.8521 |
| 0.1024 | 5.0 | 2050 | 0.4876 | 0.8589 |
| 0.0743 | 6.0 | 2460 | 0.5187 | 0.8592 |
| 0.0549 | 7.0 | 2870 | 0.5719 | 0.8572 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3