distilbert_lda_100_v1_book_qnli
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_100_v1_book on the GLUE QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3533
- Accuracy: 0.8483
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 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: 50
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.4749 |
1.0 |
410 |
0.3737 |
0.8298 |
| 0.3589 |
2.0 |
820 |
0.3533 |
0.8483 |
| 0.2756 |
3.0 |
1230 |
0.3595 |
0.8506 |
| 0.201 |
4.0 |
1640 |
0.4855 |
0.8340 |
| 0.1427 |
5.0 |
2050 |
0.4893 |
0.8459 |
| 0.1037 |
6.0 |
2460 |
0.5452 |
0.8494 |
| 0.0773 |
7.0 |
2870 |
0.6410 |
0.8451 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
