Degraded Results After Retraining
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 35/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- python
- Domain
- machine-learning
Research direction
Start with the official SFT training entry point and the lmms-eval run mentioned in the report. Reproduce the comparison between the release and retrained models on MathVista, MathVision, MathVerse, and MMMU-Pro, then determine whether the observed gap is expected or indicates a training or evaluation problem.
Written by the indexing model from the issue text.
Description
Hey the team,
Thanks for the great work. I have a problem about the SFT training: I found that the model performance after running the official SFT training seems to be lower than the reported number as shown the table below. Though I'm temporarily using Qwen3-VL-8B-Instruct as the judge, there's still a huge gap between the release model and the re-trained model, especially on large datasets like MathVista, MathVision, MathVerse, and MMMU-Pro. Some of them are outside the resulting stderr from the lmms-eval, making me feel concerning.
I haven't run the RL and compared with their downstream results yet but just wanna know if that's normal or not. Looking forward to your guidance. Thanks!
- Dominant language
- Python
- Stars
- 166
- Forks
- 5
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
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.
More from EvolvingLMMs-Lab/OpenMMReasoner
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
EvolvingLMMs-Lab/OpenMMReasoner#12 · 1 comment ·
-
[Question] Details about DAPO training (entropy behavior, clip_high, dynamic sampling, loss design)Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
EvolvingLMMs-Lab/OpenMMReasoner#11 · 1 comment ·
-
training timeOpen
Difficulty 1/5 Under an hour Newbie friendliness 20/100
EvolvingLMMs-Lab/OpenMMReasoner#9 · 1 comment ·
-
Difficulty 1/5 Under an hour Newbie friendliness 20/100
EvolvingLMMs-Lab/OpenMMReasoner#7 · 1 comment ·
All issues in EvolvingLMMs-Lab/OpenMMReasoner
Similar issues
-
good first issue tools
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
bug deferred domain:ci P1
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
docling-project/docling-mcp#147 ·
-
issue: A pipe model's Valves button ignores the Allow Chat Valves permissionPossibly taken A pull request linked to this issue is open or already merged. Openbug confirmed issue
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
open-webui/open-webui#32771 · 1 comment ·
Maintainers usually reply within 1 day
-
Scheduled Security Scan is failing on mainPossibly taken @pkupt claimed this today. Opensecurity-scan-failure
Difficulty 1/5 1-3 hours Newbie friendliness 74/100
semantica-agi/semantica#2045 ·
Maintainers usually reply within 2 days