有个疑问，计算Loss的时候并不是以reward_token_id最终loss计算的，为什么推理的时候可以以reward_token_id为准呢？
Open
- Dominant language
- Python
- Stars
- 5.2k
- Forks
- 448
- Avg merge
- 3d 15h
- Merged PRs (30d)
- 26
Description
https://github.com/InternLM/xtuner/blob/081c8ca874bdbf7a7f8cd0a9e4cba503eaaa7bba/xtuner/model/reward.py#L311
Contributor guide
Assessment
This issue has not been assessed yet.