mindspore-ai / mindspore-ai/hyper-parallel
[fully_shard]处理chunk_loss时，报错unsharded_param.grad is none
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 53
- Forks
- 63
- Avg merge
- 23h 45m
- Merged PRs (30d)
- 63
Description
该问题是怎么引起的？
fully_shard处理chunk_loss时，报错unsharded_param.grad is none，原因在于在某些求导场景中，dw会延迟到最后一个dx获取后才准备好
重现步骤
报错信息
schema_version: 1
source: gitcode
gitcode_repo: mindspore/hyper-parallel
gitcode_issue: 65
source_url: https://gitcode.com/mindspore/hyper-parallel/issues/65
Contributor guide
No contributing guide indexed for this repository
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 locating the fully_shard handling for chunk_loss and reproduce the reported unsharded_param.grad is none failure. Trace when dw becomes ready relative to the final dx; done when the affected differentiation scenario completes without the missing-gradient error and the reproduction is covered by a regression test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100