Commit Graph

40 Commits

Author SHA1 Message Date
hiyouga
8c57169eb7 fix #6546
Former-commit-id: 870f23d7ea
2025-01-07 06:30:44 +00:00
hiyouga
813f5919a3 fix #6482
Former-commit-id: 6f5bb3b8e5
2024-12-30 06:03:07 +00:00
hiyouga
3bcb4633ca fix #6448
Former-commit-id: 2719867982
2024-12-27 16:54:39 +00:00
hiyouga
47c2d91933 support report custom args
Former-commit-id: 5111cac6f8
2024-12-21 21:42:45 +00:00
hoshi-hiyouga
547f76e56e Merge pull request #6401 from Zeyi-Lin/hiyouga/swanlab
feat: add swanlab for experiment tracking and visualization.
Former-commit-id: 947e22a4a3
2024-12-21 14:09:33 +08:00
ZeYi Lin
cc703b58f5 fix: by hiyouga suggestion
Former-commit-id: 3a7ea2048a
2024-12-20 16:43:03 +08:00
hiyouga
95d3c2620b support disable shuffling
Former-commit-id: c7cedc7569
2024-12-19 08:53:21 +00:00
hiyouga
6f1e450739 fix mrope
Former-commit-id: 2811814fc4
2024-12-12 15:08:17 +00:00
hiyouga
c2766af6f4 fix dpo metrics
Former-commit-id: 4270f7dfb9
2024-11-02 20:59:01 +08:00
hiyouga
584ce3a105 fix incorrect loss value for vlms
Former-commit-id: 30567a1487
2024-10-30 08:56:46 +00:00
hiyouga
825ea1c72d fix #5747
Former-commit-id: ae045c884f
2024-10-29 10:47:04 +00:00
hiyouga
0d8aa6e6ef use pre-commit
Former-commit-id: 21db8ed2f4
2024-10-29 09:07:46 +00:00
hiyouga
7ccb86b215 add docstrings, refactor logger
Former-commit-id: 54c6905937
2024-09-08 00:56:56 +08:00
hiyouga
d5ea05cfff update get template
Former-commit-id: dabad5570b
2024-09-04 22:36:20 +08:00
hiyouga
22deca0e9e lazy image load
Former-commit-id: 47ea97fb1b
2024-09-04 02:27:08 +08:00
hiyouga
bfdcc6bacf add rlhf-v dataset
Former-commit-id: 8e49940746
2024-09-01 22:57:41 +08:00
hiyouga
a83756b5e9 refactor mm training
Former-commit-id: 3382317e32
2024-08-30 02:14:31 +08:00
moontidef
b0d32b2041 fix: rename optimzer to optimizer
Former-commit-id: 40908a36fa
2024-08-07 10:05:01 +08:00
hiyouga
14bc7b0551 fix up
Former-commit-id: 29ebcd75d5
2024-07-15 01:04:56 +08:00
codingma
74f0d02eb8 1. add custom eval dataset support
2. merge load dataset and split dataset function


Former-commit-id: 76f3bbcfc0
2024-07-05 15:52:10 +08:00
hiyouga
835f0578c2 refactor pissa, improve llamaboard
Former-commit-id: 8baf3b22b0
2024-06-28 01:04:24 +08:00
hiyouga
a225b5a70c tiny fix about badam
Former-commit-id: 095fab58d3
2024-06-25 01:54:53 +08:00
Jonery
c779899f7b Cleaner integration.
Former-commit-id: 5c2ff1b749
2024-06-19 12:29:40 +08:00
Jonery
3a5eacb4cf Support distributed BAdam.
Former-commit-id: 0f72aac8c9
2024-06-18 12:27:47 +08:00
hiyouga
c0c6b8075a tiny fix
Former-commit-id: 38b6b0f52e
2024-06-16 01:06:41 +08:00
hiyouga
2946153cea add license
Former-commit-id: d87108daa6
2024-06-15 17:54:33 +08:00
hiyouga
81ed4d8abf fix #4209
DeepSpeed ZeRO3 has inflight param error when calling model.eval()


Former-commit-id: cf9f2d6c42
2024-06-13 02:25:50 +08:00
hiyouga
d3196318be fix #4120
Former-commit-id: f9e818d79c
2024-06-07 04:18:05 +08:00
hiyouga
8da149ba40 rename files
Former-commit-id: 74f96efef9
2024-06-07 00:09:06 +08:00
hiyouga
e898d8bbc4 update trainers
Former-commit-id: fad2591e31
2024-06-06 18:45:49 +08:00
hiyouga
6f7b6ae0c3 remove gc warnings in DPO&KTO
Former-commit-id: f9a206509e
2024-06-03 22:53:54 +08:00
hoshi-hiyouga
5d96cf146e Update trainer.py
Former-commit-id: 24499f40dc
2024-06-03 22:08:38 +08:00
enji.zhou
e58aca0602 fix KTO Trainer Sampler
Former-commit-id: 34a2c5087a
2024-06-03 21:32:38 +08:00
hiyouga
bfac965f9c update dpo, kto trainer
Former-commit-id: 7c8e01bb74
2024-05-29 00:14:29 +08:00
hiyouga
14f6cc2b7c clean kto trainer
Former-commit-id: 900e1ea622
2024-05-28 21:43:26 +08:00
hiyouga
4807c11db8 support SimPO #3900
Former-commit-id: cb63b32986
2024-05-26 23:46:33 +08:00
hiyouga
3e729798df refactor data preprocessing, fix mllm rlhf
Former-commit-id: 3a023bca2a
2024-05-24 04:08:25 +08:00
hiyouga
519d2511ae improve data process logger
Former-commit-id: a851056229
2024-05-18 22:02:42 +08:00
hiyouga
13d7b48efe improve KTO impl., replace datasets
Former-commit-id: c450ee87a3
2024-05-18 03:44:56 +08:00
enji.zhou
03956053b8 add kto
Former-commit-id: db1d5a4f51
2024-05-17 13:09:17 +08:00