GitLab

* Created DUP eval code for gsm8k

* asdiv

* Fixed fewshot=8 issue

* added results to .gitignore

* reverted unnecessary changes and moved results + gsm8k_dup out of repo to prepare for pull req

* fixed whitespace and unintentional hardcoded version change information

* created mbpp task

* Reverted changes re. mbpp to save for a future Pull req

* reverted metrics.py to previous commit

* updated asdiv readme to include informaiton about new asdiv_cot_llama task

* Apply suggestions from code review

---------
Co-authored-by: Alexander Detkov <alexander.d.detkov@gmail.com>
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>