revert lr dpo (#22)

sail-sg · Dec 1, 2024 · c638ce4 · c638ce4
1 parent 870e4a2
commit c638ce4
Showing 1 changed file with 1 addition and 4 deletions.
diff --git a/oat/learners/dap.py b/oat/learners/dap.py
@@ -223,10 +223,7 @@ def get_batch_logps(
 
         if self.algo != DAPAlgo.BNF:
 
-            if self.algo == DAPAlgo.LR_DPO:
-                length = torch.min(loss_masks.sum(-1))
-            else:
-                length = loss_masks.sum(-1)
+            length = loss_masks.sum(-1)
 
             if average_log_prob:
                 return (target_logps * loss_masks).sum(-1) / length