OpenEuroLLM / OpenEuroLLM/Taskboard

Warmup evals

Open
#102 0 comments 0 reactions 3 assignees View on GitHub

@timurcarstensen is already working on this.

Since Sep 23, 2025.

Dominant language
No language data
Stars
3
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Some of the open-sci experiments with variable warmup period are here

https://huggingface.co/collections/open-sci/open-sci-ref-001-c4-6880bb9ec71ae334ab2d4bf2

Executed on 1.3B scale, for 50B and 300B token budget.

The task is to evaluate those checkpoints with our eval collection and figure out whether

  • long warmup 25000 for 300B is indeed better performing than 20000, 10000
  • short warmup of 1000 is critical for 50B (longer warmup worse)

Contributor guide

No contributing guide indexed for this repository

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.