modelscope / modelscope/ms-swift
GRPO 多任务的swanlab曲线有问题，因为当前批次内无该任务数据时指标为None
Open
Nobody has claimed this yet.
bug
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Checklist / 检查清单
- I have searched existing issues, and this is a new bug report. / 我已经搜索过现有的 issues，确认这是一个新的 bug report。
Bug Description / Bug 描述
How to Reproduce / 如何复现
我已经在不同的reward中加了对应的task判断。
if t != "fire_inspection":
rewards.append(None)
continue
if t != "blank_inspection":
rewards.append(None)
continue
Additional Information / 补充信息
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the GRPO multi-task run with the reward conditions shown in the report, then trace where None-valued rewards are consumed for SwanLab logging. Confirm the expected curve behavior when a batch has no data for a task, and add or update coverage if the relevant test entry point is found.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100