# Fine-tune with SFTTrainer

**URL:** <https://discuss.huggingface.co/t/fine-tune-with-sfttrainer/101516>\
**Category:** Beginners\
**Created:** [August 8, 2024, 1:46pm UTC](https://discuss.huggingface.co/t/fine-tune-with-sfttrainer/101516 "2024-08-08T13:46:27Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![user7896](https://avatars.discourse-cdn.com/v4/letter/u/c5a1d2/32.png) [@user7896](https://discuss.huggingface.co/u/user7896)\
**Post date:** [August 8, 2024, 1:46pm UTC](https://discuss.huggingface.co/t/fine-tune-with-sfttrainer/101516/1 "2024-08-08T13:46:27Z")

</div>

When we use a sequence of messages for training (e.g. user message #1, assistant message #1, user message #2, assistant message #2), is the model trained to generate only the last message (i.e. assistant message #2) of the assistant in the sequence, and all previous messages are used as context, or is the model trained to generate each assistant message separately (i.e. both assistant message #1 and assistant message #2)? That is, what is the target of the model?