huggingface / huggingface/lighteval
[BUG] Cache management failed for tasks using MetricGrouping
Open
bug
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 555
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 1
Description
## Describe the bug
SampleCache:_get_task_hash uses LightevalTaskConfig:__str__ to compute task hash, but LightevalTaskConfig:__str__
doesn't handle tasks using MetricGrouping correctly, for MetricGrouping field corpus_level_fn is a dict, so another level of loop is needed.
## To Reproduce
Cache doesn't work for "leaderboard|truthfulqa:mc|0"
## Expected behavior
Cache should work
## Version info
0.11.0
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.