EleutherAI/lm-evaluation-harness

Add Regression Testing

Open

#1,883 opened on May 24, 2024

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (3,306 forks)auto 404
feature requestgood first issuehelp wanted

Repository metrics

Stars
 (12,755 stars)
PR merge metrics
 (Avg merge 15d 7h) (11 merged PRs in 30d)

Description

As per the issue title.

It would be great to have regression tests for some core tasks set up, checking that 1. some key tasks' scores don't regress or change and 2. that the printouts for results stay the same (results tables).

ideally, we'd have:

  • on-CPU tests (with limit=10) that can always run
  • full on-GPU tests that can be run when desired for larger changes.

If any contributors are interested in taking this on, it'd be a huge help! Otherwise, I hope to get to this.

Contributor guide

Research direction
Examine the existing test suite in the repository, understand the core tasks and their scoring, and plan regression tests that capture scores and printouts for a limited set of examples.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitPython
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50