github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-08 12:30:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

add orpo

Browse Source
This commit is contained in:
YeAnbang
2024-06-27 07:20:28 +00:00
parent f3de5a025c
commit c8d1b4a968
12 changed files with 783 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
applications/ColossalChat/coati/trainer/dpo.py
View File

@@ -134,7 +134,6 @@ class DPOTrainer(SLTrainer):
batch["reject_attention_mask"],
batch["reject_loss_mask"],
)
reject_loss_mask[:, -1] = False
batch_size = chosen_input_ids.size()[0]
actor_all_logits = self.model(