164 Commits

Author SHA1 Message Date
hiyouga
a16786d8ba fix #4090
Former-commit-id: 67fe822324a9f830175e44f89acdd9d759b38852
2024-06-06 00:50:32 +08:00
hiyouga
6f7b6ae0c3 remove gc warnings in DPO&KTO
Former-commit-id: f9a206509ec8cd3abfad8bd924c9387317a4ead8
2024-06-03 22:53:54 +08:00
hoshi-hiyouga
5d96cf146e Update trainer.py
Former-commit-id: 24499f40dc1d9db448a3328d2a75c60eec27feb9
2024-06-03 22:08:38 +08:00
enji.zhou
e58aca0602 fix KTO Trainer Sampler
Former-commit-id: 34a2c5087a174a807e5a11cae3748bcaaaf13550
2024-06-03 21:32:38 +08:00
Uminosachi
0de4e1e9e2 Set scheduler_specific_kwargs to get_scheduler
Former-commit-id: 14e97dc1192f6cf94ab99eb3a9b8c64029040384
2024-05-31 13:45:39 +09:00
hiyouga
468d0e7ed1 10x generate in ppo w/ zero3
https://github.com/huggingface/trl/pull/1483

Former-commit-id: 65cd8bdbdbe1b19250ecd813aeb72c8e00ef2f9c
2024-05-29 00:23:23 +08:00
hiyouga
bfac965f9c update dpo, kto trainer
Former-commit-id: 7c8e01bb74bb2d2da5dba5059a9c262e4730b802
2024-05-29 00:14:29 +08:00
hiyouga
14f6cc2b7c clean kto trainer
Former-commit-id: 900e1ea622a2ffa45c5e2a359471962563fabca7
2024-05-28 21:43:26 +08:00
hiyouga
4807c11db8 support SimPO #3900
Former-commit-id: cb63b32986c43f97994211ec34dc5928fc3bb9d7
2024-05-26 23:46:33 +08:00
hiyouga
3e729798df refactor data preprocessing, fix mllm rlhf
Former-commit-id: 3a023bca2a502810a436cfba7708df164754ea62
2024-05-24 04:08:25 +08:00
hiyouga
519d2511ae improve data process logger
Former-commit-id: a851056229f37391023627180b5712ed64ae3528
2024-05-18 22:02:42 +08:00
hiyouga
13d7b48efe improve KTO impl., replace datasets
Former-commit-id: c450ee87a35ff9235f9b695b0de2e042b2971178
2024-05-18 03:44:56 +08:00
enji.zhou
03956053b8 add kto
Former-commit-id: db1d5a4f51faae61fe18666057353747b01f5b8d
2024-05-17 13:09:17 +08:00
hiyouga
cae823ddf0 rename package
Former-commit-id: 308edbc4260d45907b4a9d3a45ec21d83e48aacb
2024-05-16 18:39:08 +08:00