Commits · fdd3dbc3b2871d6a0a5433bfa42f56490ee058ab · gaoqiong / lm-evaluation-harness

25 Nov, 2022 1 commit
- Add the original `LAMBADA` dataset · bfa57687
  jon-tow authored Nov 24, 2022
  
  bfa57687
03 May, 2022 1 commit
- add pre-commit · 121b7096
  Fabrizio Milo authored May 02, 2022
  
  121b7096
18 Mar, 2022 1 commit
- Refactor `Task` download · 7c9da714
  Jonathan Tow authored Mar 11, 2022
  
  7c9da714
28 Feb, 2022 2 commits
- Make citations module-level constants · 3f13d15f
  Jonathan Tow authored Feb 28, 2022
  
  3f13d15f
- Add citations and descriptions to all tasks · a1aceacd
  Jonathan Tow authored Feb 28, 2022
  
  a1aceacd
30 Jan, 2022 1 commit
- Added more eval tasks and fixed directory error tasks · bb0eafbb
  Quentin Anthony authored Jan 30, 2022
  
  bb0eafbb
08 Jan, 2022 1 commit
- Actually it shouldn't be hard to fix it to be compatible with future version · c65412e5
  thomasw21 authored Jan 08, 2022
  
  c65412e5
30 Oct, 2021 1 commit
- Replace the `fewshot_description` API with a `description_dict` based interface · 8ac99269
  Jonathan Tow authored Oct 30, 2021
  
  8ac99269
24 Jun, 2021 1 commit
- Don't download lambada if it already exists · 75519897
  sdtblck authored Jun 24, 2021
  
  75519897
05 Jun, 2021 2 commits
- convert all enabled tasks to use best_download for better download robustness · 20229183
  Leo Gao authored Jun 04, 2021
  
  20229183
- Add task versioning · 105fa974
  Leo Gao authored Jun 04, 2021
  
  105fa974
11 May, 2021 1 commit
- switch lambada over to wget while researcher2 fixes best-download · ab8da1f0
  Leo Gao authored May 11, 2021
  
  ab8da1f0
27 Mar, 2021 1 commit
- Remove unused imports and format imports · d5d19219
  Jonathan Tow authored Mar 26, 2021
  
  d5d19219
13 Feb, 2021 1 commit
- Update lambada data location · e5a9de80
  Leo Gao authored Feb 12, 2021
  
  e5a9de80
12 Feb, 2021 1 commit
- metrics file · 1fb90b91
  & authored Feb 12, 2021
  
  1fb90b91
08 Feb, 2021 1 commit
- LAMBADA metric consistency change · dcd44d22
  Leo Gao authored Feb 07, 2021
  
  dcd44d22
05 Feb, 2021 1 commit
- Add task table · c0fbf9e8
  Leo Gao authored Feb 04, 2021
  
  c0fbf9e8
04 Feb, 2021 2 commits

Leo Gao authored Feb 03, 2021

- Extract evaluator (still needs work to clean up)
- Add tests for evaluator
- Fix all the things that break on the new tests
- Misc cleanup

778e0f91

Fix lambada · b57d059a
Leo Gao authored Feb 03, 2021

b57d059a

03 Feb, 2021 1 commit
- Refactor `Dataset` naming and `HFTask` properties · a60ef6fa
  Jonathan Tow authored Feb 02, 2021
  
  a60ef6fa
01 Feb, 2021 1 commit
- Fix linting problems · fe4a1efd
  Leo Gao authored Feb 01, 2021
  
  fe4a1efd
30 Jan, 2021 1 commit
- add evaluation for TriviaQA dataset based on loglikelihood · 0601d0bb
  Anthony DiPofi authored Jan 30, 2021
  
  0601d0bb
29 Jan, 2021 2 commits
- Update dependencies · f37dcab6
  Jon Tow authored Jan 29, 2021
  
  f37dcab6
- Implement LAMBADA · 822fcc6f
  Leo Gao authored Jan 28, 2021
  
  822fcc6f
22 Jan, 2021 2 commits
- Remove rewrite reminder comment from everything except SuperGLUE · f4120e59
  Leo Gao authored Jan 21, 2021
  
  f4120e59
- Clean up code, remove some footguns · e31b4b31
  Leo Gao authored Jan 21, 2021
  
  e31b4b31
06 Jan, 2021 1 commit
- Add comments to remind that evaluation needs to be written for the new framework · 2d2dbf96
  Leo Gao authored Jan 05, 2021
  
  2d2dbf96
05 Jan, 2021 1 commit
- Add reminder to rewrite · 08dc67ea
  Leo Gao authored Jan 05, 2021
  
  08dc67ea
24 Oct, 2020 1 commit
- update lambada for new dataset class · 8e4ff678
  Anish Thite authored Oct 24, 2020
  
  8e4ff678
05 Oct, 2020 2 commits
- add lambada · 08f2ed6e
  sdtblck authored Oct 05, 2020
  
  08f2ed6e
- add lambada · fb8c3df9
  sdtblck authored Oct 05, 2020
  
  fb8c3df9