modelscope / modelscope/DiffSynth-Studio
accelerate_config_zero3_14B num_frames=81
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
When I use the following deepspeed configuration (accelerate_config_zero3_14B
accelerate_config_zero3_14B.yaml
), training with num_frames=81 results in the following error:
However, there is no problem with snum_frames=49.
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 with the attached accelerate_config_zero3_14B.yaml and train_log_dit_14B_81.txt, then compare the failing num_frames=81 run with the working num_frames=49 case. Identify the cause of the reported training error and verify that the proposed change allows the 81-frame configuration to train successfully.
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
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100