NaN loss during training
Open
- Dominant language
- Python
- Stars
- 2k
- Forks
- 301
- PR merge metrics
- No merged PRs in 30d
Description
跑LatticeBERT里面fine-tuning a AFQMC classification model的样例，参数也没动，标注数据集，迭代几次就loss NaN？
Contributor guide
No contributing guide indexed for this repository
Research direction
Reproduce the LatticeBERT AFQMC fine-tuning example with the stated unchanged parameters and inspect when the loss first becomes NaN. No file, test, environment, or training entry point is identified; done requires a reproducible diagnosis and a verified fix or a clearer failure report.
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