thu-ml / thu-ml/TurboDiffusion
loss 0.0000
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 277
- Avg merge
- 2h 57m
- Merged PRs (30d)
- 2
Description
你好，我按照readme训练SLA时，只用了数据集中的一小部分数据，发现训练日志中Iteration 1: Hit counter: 1/5000 | Loss: 0.000000000 |， Loss一直是0， 我把c.trainer.run_validation设置为true时，在validate方法中 with model.pipe.ema_scope(context="Validation", is_cpu=False):
for val_iter, data_batch in enumerate(dataloader_val): 这里会报错，不知道是什么原因
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 README training instructions and the SLA training entry point, reproducing the zero-loss log on the reduced dataset. Then inspect trainer.run_validation, validate, model.pipe.ema_scope, and dataloader_val; capture the validation traceback and confirm that both the loss behavior and validation failure are understood and resolved.
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