81 Commits

Author SHA1 Message Date
hiyouga
51a0016873 optimize predict vram
Former-commit-id: a244f143f48a01910ce1cd56c0855ef11d62a72a
2024-08-30 23:08:45 +08:00
hiyouga
a83756b5e9 refactor mm training
Former-commit-id: 3382317e32f88ed377d3e7759bdeaf0f2559d22a
2024-08-30 02:14:31 +08:00
hiyouga
21d3976eea fix #5295
Former-commit-id: ad72f3e06593f124d661d61774def336511716e0
2024-08-29 20:30:18 +08:00
hiyouga
1494fa1f18 fix #5305
Former-commit-id: 364b757e306f7a154359a2bc8245a839f39c4fab
2024-08-29 20:16:01 +08:00
hiyouga
7b5834b2dd tiny fix
Former-commit-id: f6ae4e75ddaeb4ac4a527f0141ac5b1afefde10e
2024-08-27 12:49:32 +08:00
hiyouga
daebca2368 tiny fix
Former-commit-id: c8b4c7fee5398654683b713ad5c03b5daf13218a
2024-08-20 00:10:52 +08:00
liu-zichen
8a7ab8ab21 fix lr not change
Former-commit-id: ddee718b31a5bf3cb39c5adf3f8e0be8fddf9dbb
2024-08-13 16:33:34 +08:00
hiyouga
5eacd17090 add adam_mini to readme
Former-commit-id: e2a28f51c635d64ff9de65a37087d89356bdedcc
2024-08-09 20:02:03 +08:00
moontidef
44f7c4dd56 feat: add support for adammini
Former-commit-id: 82bc15dc795f95768b81c25eaaabdc613da30cd8
2024-08-07 10:08:22 +08:00
moontidef
b0d32b2041 fix: rename optimzer to optimizer
Former-commit-id: 40908a36fae3393715f75156867c11e6373fabad
2024-08-07 10:05:01 +08:00
hiyouga
20013e130b fix #5048
Former-commit-id: b7ca6c8dc14f689d0df16684a6121cc0ec24f8ba
2024-08-05 23:48:19 +08:00
codingma
8132725f2e fix pissa save
Former-commit-id: 2c1ca9f7425b84e158fef527fd6e13297c8253c6
2024-07-29 10:44:34 +08:00
hiyouga
e1e01d7efd add unittest
Former-commit-id: 608de799a21f37319bf31c04c0aa50c4542ec757
2024-07-19 01:06:27 +08:00
hiyouga
3c7b10b1fa fix metrics #4786
Former-commit-id: beec77a0898a39d94f41c23920415f5b4873a23a
2024-07-17 00:47:00 +08:00
hiyouga
e90fae61f4 support batch_eval_metrics, fix #4826
Former-commit-id: d774b94f124923829b2eae428e25199d503ebfcb
2024-07-17 00:33:00 +08:00
hiyouga
84e6715423 fix #4820
Former-commit-id: fd8cc490084aba9b5155eaaaf26129efd2871fa3
2024-07-15 22:32:07 +08:00
hiyouga
14bc7b0551 fix up
Former-commit-id: 29ebcd75d55f70f2891632eba187b643cc3a9e51
2024-07-15 01:04:56 +08:00
hoshi-hiyouga
2b22a7da48 Merge pull request #4691 from codemayq/feature-suppot-eval-dataset
add eval dataset support

Former-commit-id: 15b399a82f45b08fc07d2957884fb7821eba9fd9
2024-07-15 01:00:34 +08:00
hzhaoy
955e01c038 tiny fix
Former-commit-id: 8bab99c5829a80752e461cf65a9124fdea609676
2024-07-12 00:28:44 +08:00
hoshi-hiyouga
4edd7c3529 Update callbacks.py
Former-commit-id: 39cd89ce17220dc50c8331299ae5af230fe40cc9
2024-07-10 13:32:20 +08:00
-.-
973aac3203 fix src/llamafactory/train/callbacks.py
Former-commit-id: cff89a2e8907f3fe89406006105cb6494e2ee993
2024-07-10 12:05:51 +08:00
hiyouga
a9ce54d143 fix #4731
Former-commit-id: 51942acee84cdb20002f8fdccf6be8c7fe9bd0d3
2024-07-10 11:32:36 +08:00
hiyouga
d7130ec635 fix ppo trainer
Former-commit-id: fb0c40011689b3ae84cc3b258bf3c66af3e1e430
2024-07-10 11:05:45 +08:00
hiyouga
aa15ca1719 fix #4742
Former-commit-id: 2f09520c0d5039a5a8be310ab668272cb4dc1bd3
2024-07-09 23:24:24 +08:00
codingma
74f0d02eb8 1. add custom eval dataset support
2. merge load dataset and split dataset function


Former-commit-id: 76f3bbcfc0e11aa41f8f5cbebc60b77b987f7901
2024-07-05 15:52:10 +08:00
hiyouga
7b3c1f29ff fix packing for eager/sdpa attn
Former-commit-id: 6fd6aa4530f81a2ed306eeb2a5167607288b62c6
2024-07-04 01:52:43 +08:00
hiyouga
3595d98b4c fix #4609
unwrap_model_for_generation(reward_model) is necessary for zero3 training


Former-commit-id: 8845e94f917b503bbee0604d7290efea7260a30c
2024-07-03 19:45:51 +08:00
hiyouga
104151d558 tiny fix
Former-commit-id: 8b1172b91085125a83a4150943873141c8bbd8bc
2024-07-03 02:31:50 +08:00
hiyouga
c9e9beee4e tiny fix
Former-commit-id: 71cdf8956e1640a1f3e5f6a4b86d28db70e72041
2024-07-02 23:06:13 +08:00
hiyouga
ea2d3f6c18 remove rlhf support for chatglm2&3
Former-commit-id: 821bb6660e57c29ebf6ac482e78dd2efb8d72437
2024-07-02 23:03:17 +08:00
hiyouga
4828bed837 upcast logits
Former-commit-id: c13ae2df19ed4cdc849bef55d04225e1a98c19b5
2024-07-02 22:32:05 +08:00
hiyouga
cc31014002 improve rlhf
Former-commit-id: c47ab6c07287fb260ea49b8b7af46bdd416f88f7
2024-07-02 22:23:08 +08:00
hiyouga
08296f4092 fix ppo callbacks
Former-commit-id: 4c296001c4b77b814e4bd6cb4049a279718cb775
2024-07-02 17:34:56 +08:00
hiyouga
2cf03017a0 tiny fix
Former-commit-id: 73280b7dc7f8b3210bb08dfc3cf34760190f585a
2024-07-01 05:43:17 +08:00
hiyouga
54e786346e add eval acc
Former-commit-id: 1856a08e87b150fa4bffcb0af703ed84d848e24b
2024-07-01 03:51:20 +08:00
hiyouga
2b006beab1 loose gemma2 attention
Former-commit-id: 2f4b89ace15b7a4d2adf16eeba9feb7de9e25d43
2024-06-29 01:42:14 +08:00
hiyouga
d3b7c489f2 add Gemma2 models
Former-commit-id: 6f63050e1b61742d5f7e48bdc62c46748031d7cb
2024-06-28 01:26:50 +08:00
hiyouga
835f0578c2 refactor pissa, improve llamaboard
Former-commit-id: 8baf3b22b0fb9624807d809832f097301982d192
2024-06-28 01:04:24 +08:00
hzhaoy
e1751f6398 fix #4579
Former-commit-id: 677c86594e4ea904fde0a557852daf54636b06ae
2024-06-27 13:49:57 +08:00
hiyouga
28e613efd0 fix #4458
Former-commit-id: 8d6cd69ac43afd4bd7c14bd02b0061455827ac9e
2024-06-26 19:52:35 +08:00
hiyouga
ad0304e147 fix #4379
Former-commit-id: cc016461e63a570142b56d50a5d11e55a96ab8db
2024-06-25 02:31:44 +08:00
hiyouga
a225b5a70c tiny fix about badam
Former-commit-id: 095fab58d3692607c9e78747b4218ae1abcf5aaf
2024-06-25 01:54:53 +08:00
hoshi-hiyouga
fe6ef6400c Merge pull request #4352 from Ledzy/main
[Enhancement] Support ZeRO-3 when using BAdam

Former-commit-id: d0f953bf5bdbfd49acc82ff055bd54889241761a
2024-06-25 01:49:13 +08:00
hiyouga
7be502c5c5 update readme
Former-commit-id: e507e60638b2e8c66f24805b3b28f6b9f98f5924
2024-06-24 18:22:12 +08:00
hiyouga
7735456561 fix templates
Former-commit-id: 4cff6a4ad55b24bf57db6be5cf817180c1ea5626
2024-06-19 17:44:05 +08:00
Jonery
c779899f7b Cleaner integration.
Former-commit-id: 5c2ff1b749a265dd3c979189ec491d8ac911a6f6
2024-06-19 12:29:40 +08:00
Jonery
3a5eacb4cf Support distributed BAdam.
Former-commit-id: 0f72aac8c9227e33ad20d2b1641b1c9faae16a5f
2024-06-18 12:27:47 +08:00
Jonery
5d59f6562a Merge remote-tracking branch 'upstream/main'
Former-commit-id: ea1f3ba5e030504e07053484f50f4cbdb37808bc
2024-06-17 18:44:51 +08:00
Jonery
756566342d adapt for badam with ds zero3
Former-commit-id: 33b437277846d4f0b64c13a0bc892ef4f345a21e
2024-06-17 18:18:10 +08:00
hiyouga
ce4a27a5f7 fix tol
Former-commit-id: 46093b5786611d99adf1fd3d42926a728fc629f8
2024-06-16 01:38:44 +08:00