jankrepl / jankrepl/gnnfit

Implement early stopping in the inner training

Open
#11 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
1
Forks
1
PR merge metrics
No merged PRs in 30d

Description

Otherwise there will be a lot of near duplicate samples

Contributor guide

No contributing guide indexed for this repository

Research direction

No file, test, or entry point is named. Start by locating the inner training loop and reading how samples are produced and training termination is handled. Done means the inner training stops early enough to avoid producing many near-duplicate samples, with behavior covered by an appropriate test.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.