lm-evaluation-harness
lm-evaluation-harness copied to clipboard
Premature `num_fewshot` check with `fewshot_as_multiturn`
main
raises a ValueError if fewshot_as_multiturn
and no num_fewshot
. However, num_fewshot
can also be set in the task YAML, which is processed later. Think we should remove this especially because num_fewshot
sets the global fewshots ignoring task specific values.
https://github.com/EleutherAI/lm-evaluation-harness/blob/b70af4f51481db15ec3068d26cde3d76dd0201e7/lm_eval/main.py#L295-L300