Lightning-AI / Lightning-AI/pytorch-lightning
`EarlyStopping` monitor `min_delta` by percentage
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 31.4k
- Forks
- 3.8k
- Avg merge
- 6d 7h
- Merged PRs (30d)
- 6
Description
### Description & Motivation
When measuring errors, there are absolute errors and relative errors. It is a good idea to monitor the percentage of `val_loss` reduction for early stopping!
### Pitch
_No response_
### Alternatives
_No response_
### Additional context
_No response_
cc @borda @carmocca @awaelchli
Contributor guide
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 by locating the EarlyStopping implementation and its existing min_delta handling, then inspect how val_loss is monitored. Define the percentage-based behavior and its interaction with absolute errors before identifying the relevant tests; done means percentage monitoring works without regressing current absolute min_delta behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100