# Sentence-bert finetuning

**URL:** <https://discuss.huggingface.co/t/sentence-bert-finetuning/170359>\
**Category:** Beginners\
**Created:** [November 13, 2025, 6:07am UTC](https://discuss.huggingface.co/t/sentence-bert-finetuning/170359 "2025-11-13T06:07:37Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mizz54112](https://avatars.discourse-cdn.com/v4/letter/m/f04885/32.png) [@Mizz54112](https://discuss.huggingface.co/u/Mizz54112)\
**Post date:** [November 13, 2025, 6:07am UTC](https://discuss.huggingface.co/t/sentence-bert-finetuning/170359/1 "2025-11-13T06:07:37Z")

</div>

> <https://github.com/huggingface/sentence-transformers/blob/master/examples/sentence_transformer/training/nli/training_nli.py>

This code on GitHub trains Sentence-BERT on an NLI dataset. The evaluation section currently uses STS. Is it possible to change this to accuracy (the correct answer rate for the NLI data)? If so, I would appreciate specific guidance on how to implement this change.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [November 13, 2025, 11:05am UTC](https://discuss.huggingface.co/t/sentence-bert-finetuning/170359/2 "2025-11-13T11:05:55Z")

</div>

Probably [something like this](https://huggingface.co/datasets/John6666/forum2/blob/main/st_ft_sts_to_nli_accuracy_1.md)…?

---

<div class="post-metadata">

**Author:** ![Mizz54112](https://avatars.discourse-cdn.com/v4/letter/m/f04885/32.png) [@Mizz54112](https://discuss.huggingface.co/u/Mizz54112)\
**Post date:** [November 14, 2025, 3:57am UTC](https://discuss.huggingface.co/t/sentence-bert-finetuning/170359/3 "2025-11-14T03:57:49Z")

</div>

Thank you for explaining it so thoroughly. It’s very easy to understand.