NVIDIA-NeMo / NVIDIA-NeMo/Gym

Clean metrics computation

Open
#3,471 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.2k
Forks
349
Avg merge
1d 23h
Merged PRs (30d)
324

Description

Use cases, pain points, and background
Right now metrics can be calculated per benchmark in any way (e.g. responses_api_agents/scicode_agent/app.py _across_run_stats) without any naming conventions nor structure (e.g. one function with clearly defined input per metric). This makes writing general code (e.g. for computing CIs) difficult.

We need a way to still provide flexibility but with clean rules.

Description:
TBD

Design:
TBD

Out of scope:
TBD
Acceptance Criteria:

  • TBD

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing responses_api_agents/scicode_agent/app.py, especially the _across_run_stats implementation, and compare how metrics are computed across benchmarks. The issue leaves the design and acceptance criteria as TBD, so the metric interface, naming rules, and definition of done need to be clarified before implementation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.