纯小白请教，LOSS到034
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
继续作者75K训练到229
LOSS到034就下不去了
有什么办法吗，现在模型效果还不是很好
问题在哪，应该怎么继续训练？
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or training entry points. Start by locating the training configuration and loss calculation, then reproduce the reported plateau around 0.34 and compare the current model quality with the training settings. Done means identifying a supported cause or a concrete, documented way to continue training.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100