modelscope / modelscope/DiffSynth-Studio
DMD2训练损失震荡
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
用1张80G 的A100训练flux2-klien-base-4b的少步蒸馏版本，参数为提供的默认参数，发现损失震荡严重，用训练后的权重推理发现效果也很差，请问是否有人成功训练过呢？
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
The report names no source files, tests, or entry points; it only describes DMD2 training on flux2-klien-base-4b with default parameters and includes a loss plot. First reproduce the training setup and inspect the loss behavior and inference results. Done means identifying a reproducible cause and confirming stable loss and acceptable generated output.
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
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100