github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-22 01:48:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'grpo-latest-rebase-main' of https://github.com/hpcaitech/ColossalAI into grpo-latest-rebase-main

Browse Source
This commit is contained in:
YeAnbang
2025-08-14 19:03:04 +08:00
parent 762150cf51 94e972fda6
commit 99ba48fc40
4 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
applications/ColossalChat/coati/distributed/grpo_consumer.py
View File

@@ -530,4 +530,4 @@ class GRPOConsumer(BaseConsumer):
model = self.policy_model.unwrap()
state_dict = model.state_dict()
state_dict["consumer_global_step"] = torch.tensor([self.global_step], device=self.device)
return state_dict
return state_dict