Commit Graph

30 Commits (3dc08c8a5a03d6bb28d865d2dbaae948c27e7e9a)

Author SHA1 Message Date
Tong Li 39e2597426
[ColossalChat] Add PP support (#6001)
3 months ago
YeAnbang ed97d3a5d3
[Chat] fix readme (#5989)
4 months ago
YeAnbang 0b2d55c4ab Support overall loss, update KTO logging
4 months ago
YeAnbang 30f4e31a33
[Chat] Fix lora (#5946)
4 months ago
YeAnbang 12fe8b5858 refactor evaluation
4 months ago
Tong Li d08c99be0d
Merge branch 'main' into kto
4 months ago
Tong Li f585d4e38e
[ColossalChat] Hotfix for ColossalChat (#5910)
4 months ago
YeAnbang 544b7a38a1 fix style, add kto data sample
4 months ago
YeAnbang 09d5ffca1a add kto
4 months ago
YeAnbang b3594d4d68 fix orpo cross entropy loss
5 months ago
YeAnbang e7a8634636 fix eval
5 months ago
pre-commit-ci[bot] 8a9721bafe [pre-commit.ci] auto fixes from pre-commit.com hooks
5 months ago
YeAnbang d888c3787c add benchmark for sft, dpo, simpo, orpo. Add benchmarking result. Support lora with gradient checkpoint
5 months ago
YeAnbang 8aad064fe7 fix style
5 months ago
YeAnbang c8d1b4a968 add orpo
5 months ago
YeAnbang f3de5a025c remove debug code
5 months ago
YeAnbang 0b2d6275c4 fix dataloader
5 months ago
YeAnbang 82aecd6374 add SimPO
5 months ago
YeAnbang 84eab13078 update sft trainning script
6 months ago
YeAnbang 0d7ff10ea5 replace the customized dataloader setup with the build-in one
6 months ago
YeAnbang 45195ac53d remove local data path
6 months ago
YeAnbang 62eb28b929 remove duplicated test
6 months ago
YeAnbang 7ae87b3159 fix training script
6 months ago
YeAnbang 0b4a33548c moupdate ci tests, st ci test cases passed, tp failed in generation for ppo, sp is buggy
6 months ago
YeAnbang 7e65b71815 run pre-commit
6 months ago
YeAnbang 929e1e3da4 upgrade ppo dpo rm script
6 months ago
YeAnbang 7a7e86987d upgrade colossal-chat support tp_group>1, add sp for sft
6 months ago
Hongxin Liu 7f8b16635b
[misc] refactor launch API and tensor constructor (#5666)
7 months ago
Hongxin Liu 641b1ee71a
[devops] remove post commit ci (#5566)
8 months ago
YeAnbang df5e9c53cf
[ColossalChat] Update RLHF V2 (#5286)
8 months ago