OpenEuroLLM / OpenEuroLLM/Taskboard

Evaluate Prelude checkpoints using eval-framework

Open
#408 1 comment 0 reactions 1 assignee View on GitHub

@tfburns is already working on this.

Since Sep 17, 2026.

WP5
Dominant language
No language data
Stars
3
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Goal
Evaluate Prelude checkpoints using eval-framework, which includes tasks, task variants, and metrics not included in other frameworks used to evaluate Prelude to date.

Description
Evaluate the following checkpoints (tokens → checkpoint) uploaded to HF.

Pre-training:
500B → iter_0060000
1T → iter_0120000
1.5T → iter_0180000
2T → iter_0240000
2.5T → iter_0300000
3T → iter_0360000
3.5T → iter_0420000
4T → iter_0480000
4.5T → iter_0540000
5T → iter_0600000
5.5T → iter_0660000
6T → iter_0720000
6.5T → iter_0780000
7T → iter_0840000
7.5T → iter_0900000
~8T → iter_0953312

Annealing:
~8.1T -> anneal300b_iter_0964800
~8.2T -> anneal300b_iter_0979200
~8.3T -> anneal300b_iter_0989075

See the parent issue for further details.

Deliverable scope
Eval results and comparisons to baselines.

Dependencies

  1. BPB variants PR merged
  2. confirmation on

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.