8 Commits

Author SHA1 Message Date
hiyouga
125587b187 refactor evaluation, upgrade trl to 074
Former-commit-id: 442aefb925c4ff02b98aa30c49c2e01d04f6496a
2023-11-13 22:20:35 +08:00
hiyouga
5c19786f7c use seed in evaluate.py
Former-commit-id: de95b6928293e79c7e204be307c1784ce146c1b1
2023-11-06 18:17:51 +08:00
hiyouga
77781d9516 fix tokenizer padding side in evaluate.py
Former-commit-id: 641ffa2f6ee05bda5b8548286c161c30aa0bcfb6
2023-10-21 00:30:04 +08:00
hiyouga
95697652f1 fix #1232
Former-commit-id: b665e9e133bf2f6f10346c374eb0de8a96dd5c7e
2023-10-20 23:28:52 +08:00
hiyouga
c350ba0f05 add averaging in evaluation
Former-commit-id: 5310e4d1829f36619c8f224d09ec15eeaf7a4877
2023-10-10 23:16:31 +08:00
hiyouga
88f2e99c73 add CMMLU, update eval script
Former-commit-id: 4dd9b4d9829249da21c0827fb9a170335e518d93
2023-09-23 21:10:17 +08:00
hiyouga
02549e3162 update evaluate
Former-commit-id: f8ff625d76d91bc8c0b91e9c371fd68cdccdfb7e
2023-09-23 11:55:31 +08:00
hiyouga
467c30d591 move file
Former-commit-id: badd2735b56eca107d40d0068823df78d3629c14
2023-09-23 11:52:12 +08:00