OpenEuroLLM / OpenEuroLLM/Taskboard

Prelude: document training process and checkpoints

Open
#354 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

4.6 post-training T4.4 - model training
Dominant language
No language data
Stars
3
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Goal
We want to do a better job at documenting our process, and checkpoints during the training.

  • Convert checkpoints to HF format and push to HF
  • Schedule Evaluations English and Multilingual issue to track evaluation
  • Context length extension
  • Instruction tuning Post-training SFT & DPO tracking issue
  • Instruction tuning evals

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.

Research direction

Review the checklist and the linked evaluation issue 344 and post-training tracking issue 361 first. Document the training process and its checkpoints, including Hugging Face conversion, English and multilingual evaluations, context-length extension, SFT/DPO, and instruction-tuning evaluations; done means each checkpoint has a clear status and tracking reference.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.