---
language: en
tags:
- bert
- stsb
- glue
- kd
- torchdistill
license: apache-2.0
datasets:
- stsb
metrics:
- pearson correlation
- spearman correlation
---

`bert-base-uncased` fine-tuned on STS-B dataset, using fine-tuned `bert-large-uncased` as a teacher model, [***torchdistill***](https://github.com/yoshitomo-matsubara/torchdistill) and [Google Colab](https://colab.research.google.com/github/yoshitomo-matsubara/torchdistill/blob/master/demo/glue_kd_and_submission.ipynb) for knowledge distillation.  
The training configuration (including hyperparameters) is available [here](https://github.com/yoshitomo-matsubara/torchdistill/blob/main/configs/sample/glue/stsb/kd/bert_base_uncased_from_bert_large_uncased.yaml).  
I submitted prediction files to [the GLUE leaderboard](https://gluebenchmark.com/leaderboard), and the overall GLUE score was **78.9**.

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}
}
```