pretty

turbo-llm · Nov 28, 2024 · 7a6b401 · 7a6b401
1 parent 8c61d13
commit 7a6b401
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git a/turbo_alignment/settings/pipelines/train/lddpo.py b/turbo_alignment/settings/pipelines/train/lddpo.py
@@ -5,7 +5,7 @@
 
 
 class LDDPOTrainerSettings(DPOTrainerSettings):
-    lc_alpha: float = 1.0
+    lc_alpha: float
 
 
 class LDDPOTrainExperimentSettings(DPOTrainExperimentSettings):

diff --git a/turbo_alignment/trainers/lddpo.py b/turbo_alignment/trainers/lddpo.py
@@ -79,6 +79,7 @@ def concatenated_forward(
 
         public_ = chosen_mask * rejected_mask
         public_mask = torch.cat([public_, public_])
+
         public_logps = all_logps * public_mask
 
         all_logps = self.lc_alpha * all_logps + (1 - self.lc_alpha) * public_logps