Commits · 3e1bcf712e654a53d974961dc53c721675d6c8f0 · gaoqiong / lm-evaluation-harness

"configs/datasets/CLUE_ocnli/CLUE_ocnli_gen_01899f.py" did not exist on "7d346000bb8f1f7611f88dc8e003bdf8c9ae3ece"

20 Jun, 2021 1 commit
- Add MuTual test data · 3e1bcf71
  Leo Gao authored Jun 19, 2021
  
  3e1bcf71
14 Jun, 2021 1 commit
- Fix typo · 0f4e3df4
  Leo Gao authored Jun 13, 2021
  
  0f4e3df4
12 Jun, 2021 3 commits
- Test training docs too and don't cache downloads · 893ef63f
  Leo Gao authored Jun 12, 2021
  
  893ef63f
- Look at all docs of task in test · 7cbd0bba
  Leo Gao authored Jun 12, 2021
  
  7cbd0bba
- Update test data for coqa v1 · 41b0ae22
  Leo Gao authored Jun 11, 2021
  
  41b0ae22
11 Jun, 2021 1 commit
- Set dummy secret key · 7069583b
  Leo Gao authored Jun 10, 2021
  
  7069583b
10 Jun, 2021 3 commits
- Add gpt3 tests · c59cd334
  Leo Gao authored Jun 10, 2021
  
  c59cd334
- Add stable version hash for prost · 6e5b3cde
  Leo Gao authored Jun 10, 2021
  
  6e5b3cde
- Use hashed version stability test instead · f9cc0267
  Leo Gao authored Jun 10, 2021
  
  f9cc0267
08 Jun, 2021 1 commit
- make hendrycks math order deterministic · 3b990af0
  Leo Gao authored Jun 07, 2021
  
  3b990af0
05 Jun, 2021 2 commits
- Add tests to make sure task definitions don't change without the version also changing · 17c825d1
  Leo Gao authored Jun 04, 2021
  
  17c825d1
- Add task versioning · 105fa974
  Leo Gao authored Jun 04, 2021
  
  105fa974
12 May, 2021 2 commits

Janitor testing and changes · 7cb91943

researcher2 authored May 12, 2021

Small fixes to python version of Janitor, cpp version named properly for import but code doesn't work - may or may not fix in the future.

Add unit tests for python version of Janitor.

7cb91943

Add pile 13gram processing. · 2a11129d
researcher2 authored May 12, 2021

2a11129d

11 May, 2021 1 commit
- Make bootstrap_iters configurable and fix some tests · 7a39d68b
  Leo Gao authored May 11, 2021
  
  7a39d68b
10 May, 2021 6 commits
- Add comment · 7f7673ec
  Leo Gao authored May 10, 2021
  
  7f7673ec
- Fix tests · 59aff21d
  Leo Gao authored May 10, 2021
  
  59aff21d
- Use sample stddev · 02249855
  Leo Gao authored May 10, 2021
  
  02249855
- Make bootstrap test work · 82a538d3
  Leo Gao authored May 10, 2021
  
  82a538d3
- Use sample stddev · 5452fddb
  Leo Gao authored May 10, 2021
  
  5452fddb
- Make bootstrap test work · baf54a03
  Leo Gao authored May 10, 2021
  
  baf54a03
05 May, 2021 2 commits
- Fix some things for tests · 80a739eb
  Leo Gao authored May 05, 2021
  
  80a739eb
- Begin refactoring perplexity code · b0cf0163
  Leo Gao authored May 04, 2021
  
  b0cf0163
04 May, 2021 1 commit
- adding tests sortof · ee5467ff
  Jason Phang authored May 03, 2021
  
  ee5467ff
03 May, 2021 1 commit
- Test bootstrapping · 218d105d
  Leo Gao authored May 03, 2021
  
  218d105d
15 Apr, 2021 2 commits
- Add some more tests to test is_greedy · 8f4d1b49
  Leo Gao authored Apr 14, 2021
  
  8f4d1b49
- Actually fix problems and make tests pass · 31c29e3b
  Leo Gao authored Apr 14, 2021
  
  31c29e3b
11 Apr, 2021 1 commit
- Add more gpt2 tests · eec18018
  Leo Gao authored Apr 11, 2021
  
  eec18018
27 Mar, 2021 3 commits
- Remove unused imports and format imports outside of `lm_eval` module · 9a9c8e3c
  Jonathan Tow authored Mar 27, 2021
  
  9a9c8e3c
- Revert evaluator change · 1a05b8cf
  Leo Gao authored Mar 26, 2021
  
  1a05b8cf
- Fix stuff and make tests pass · c971fa82
  Leo Gao authored Mar 26, 2021
  
  c971fa82
14 Feb, 2021 1 commit
- Fix CoQA for tests · 431e53de
  Leo Gao authored Feb 14, 2021
  
  431e53de
11 Feb, 2021 3 commits
- Undo change to test · 4a64031c
  Leo Gao authored Feb 10, 2021
  
  4a64031c
- Fixes to make greedy_until work · 7b649ded
  Leo Gao authored Feb 10, 2021
  
  7b649ded
- Implement GPT2 greedy_until · e8f9dc71
  Leo Gao authored Feb 10, 2021
  
  e8f9dc71
08 Feb, 2021 2 commits
- LM: handle empty context · 359114fd
  Leo Gao authored Feb 07, 2021
  
  359114fd
- Add tests for {val,test}_docs determinism · 442f843c
  Leo Gao authored Feb 07, 2021
  
  442f843c
05 Feb, 2021 1 commit
- Add test to make sure right space conventions are used · 049dfa34
  Leo Gao authored Feb 04, 2021
  
  049dfa34
04 Feb, 2021 2 commits

Massive refactor · 778e0f91

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

Add tests for GPT2 · 8eada53b
Leo Gao authored Feb 03, 2021

8eada53b