GitLab

* add fix fordeciding if stderr is N/A or not

* process N/A

* tuple should be considered as well

* set option to keep callable as callable

* add ruff and isort. remove black and flake8

* remove unnecessary dependencies

* remove dependency from table

* change order

* ran ruff

* check 3.9

* exclude evaluator

* update CI workflow

* use ruff config in pyproject.toml

* test

* add isort rules to ruff

* sort imports

* import `make_table`

* try stages for no-commit-to-branch

* turn on mypy for pre-commit

* test

* test

* test

* change no-commit-to-branch to default

* nits

* fixed dependency

* save progress

* fixed issue with table only showing 1 group

* store aliases directly in results_agg

* removed unused parts

enables tasks of different group but same task_alis (for example, if evaluating on different versions of MMLU