---
language: en
tags:
- bert
- qnli
- glue
- torchdistill
license: apache-2.0
datasets:
- qnli
metrics:
- accuracy
---

`bert-base-uncased` fine-tuned on QNLI dataset, using [***torchdistill***](https://github.com/yoshitomo-matsubara/torchdistill) and [Google Colab](https://colab.research.google.com/github/yoshitomo-matsubara/torchdistill/blob/master/demo/glue_finetuning_and_submission.ipynb).  
The hyperparameters are the same as those in Hugging Face's example and/or the paper of BERT, and the training configuration (including hyperparameters) is available [here](https://github.com/yoshitomo-matsubara/torchdistill/blob/main/configs/sample/glue/qnli/ce/bert_base_uncased.yaml).  
I submitted prediction files to [the GLUE leaderboard](https://gluebenchmark.com/leaderboard), and the overall GLUE score was **77.9**.

Yoshitomo Matsubara: **"torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP"** at *EMNLP 2023 Workshop for Natural Language Processing Open Source Software (NLP-OSS)*

[[Paper](https://aclanthology.org/2023.nlposs-1.18/)] [[OpenReview](https://openreview.net/forum?id=A5Axeeu1Bo)] [[Preprint](https://arxiv.org/abs/2310.17644)]  
```bibtex
@inproceedings{matsubara2023torchdistill,
  title={{torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP}},
  author={Matsubara, Yoshitomo},
  booktitle={Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)},
  publisher={Empirical Methods in Natural Language Processing},
  pages={153--164},
  year={2023}
}
```