Flight Log / stanford-crfm/levanter #1009
Fix dataset union for evaluation configs — a OpenAI Codex (OpenAI) flight by Ahmed Ahmed
Ahmed Ahmed (@ahmeda14960) opened this OpenAI Codex (OpenAI) pull request in stanford-crfm/levanter on Jun 23, 2025; merged clean in 1 min, merged by @ahmeda14960: +28 −10, 4 files, 0 reviews.
Flown by
- Lines
- +28 −10
- Files
- 4
- Commits
- 1
- Reviews
- 0
- To merge
- 1 min
- Task
- fix
Line and file counts are summed per commit from the AIDev dataset; GitHub's net diff can be smaller.
OpenAI Codex worked on dataset union for evaluation configs, adding Hugging Face dataset IDs via SingleDatasetLMConfig. The change spans four files with 28 additions and 10 deletions in one commit. A pytest run failed with ModuleNotFound. The pull request merged clean in 0.01 hours, with no review rounds or change requests.
From the pull request description
## Summary - allow specifying HF dataset IDs in evaluation scripts by using `SingleDatasetLMConfig` - update `eval_lm.py`, `eval_sliding_lm.py`, `viz_logprobs.py`, and `lora_lm.py` ## Testing - `black` formatting - `isort` import ordering - `pytest -k "eval_lm or viz_lm" -q` *(fails: ModuleNotFound…
Excerpt (first 300 characters) — the full description is on GitHub.
View the pull request on GitHub →
This is your flight? Claim it — sign in with GitHub. Ownership is proven by the sign-in: the account that opened the PR is the only one that can claim it.
Flight timeline
- —committedAhmed Ahmed
- Jun 23, 2025labeledahmeda14960
- Jun 23, 2025mergedahmeda14960
- Jun 23, 2025closedahmeda14960
Read next
Cite this flight: AgentRiders Flight Log, stanford-crfm/levanter#1009, record updated Nov 4, 2026, https://agentriders.com/logs/stanford-crfm/levanter/1009/
Data from public GitHub activity; this page is not affiliated with GitHub or the repository.