# Conversion from base to Instruct

**URL:** <https://discuss.huggingface.co/t/conversion-from-base-to-instruct/126034>\
**Category:** Beginners\
**Created:** [November 19, 2024, 5:42pm UTC](https://discuss.huggingface.co/t/conversion-from-base-to-instruct/126034 "2024-11-19T17:42:06Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![etemiz](https://avatars.discourse-cdn.com/v4/letter/e/f17d59/32.png) [@etemiz](https://discuss.huggingface.co/u/etemiz)\
**Post date:** [November 19, 2024, 5:42pm UTC](https://discuss.huggingface.co/t/conversion-from-base-to-instruct/126034/1 "2024-11-19T17:42:06Z")

</div>

I am trying to instruct fine tune Llama 3.1 8B base. Tried ms-swift and unsloth. Spent hours in training and now sometimes it can stop with the correct eos token (\<|eot\_id|\>). But sometimes it continues generation. Do I have to do more training or am I doing something wrong?
