github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-06 11:32:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Coati] Train DPO using PP (#6054)

Browse Source 
* update dpo

* remove unsupport plugin

* update msg

* update dpo

* remove unsupport plugin

* update msg

* update template

* update dataset

* add pp for dpo

* update dpo

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add dpo fn

* update dpo

* update dpo

* update dpo

* update dpo

* minor update

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update loss

* update help

* polish code

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Tong Li
2024-10-11 19:32:00 +08:00
committed by GitHub
parent dc2cdaf3e8
commit 4c8e85ee0d
8 changed files with 529 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
applications/ColossalChat/examples/training_scripts/train_sft.py
View File

@@ -68,7 +68,7 @@ def train(args):
Default torch ddp plugin without any acceleration, for
debugging purpose acceleration, for debugging purpose
"""
plugin = TorchDDPPlugin(find_unused_parameters=True if args.grad_checkpoint is False else False)
plugin = TorchDDPPlugin(find_unused_parameters=not args.grad_checkpoint)
elif args.plugin == "gemini":
plugin = GeminiPlugin(
precision=args.mixed_precision,