fix dpo&kto oom (PaddlePaddle#9390)

DesmonDay · Nov 7, 2024 · d02c406 · d02c406
1 parent a3c3800
commit d02c406
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 8 deletions.
diff --git a/paddlenlp/trl/dpo_criterion.py b/paddlenlp/trl/dpo_criterion.py
@@ -287,10 +287,10 @@ def forward(
         )
         loss = dpo_loss + sft_loss
         if self.use_infohub:
-            infohub.policy_chosen_logps.append(policy_chosen_logps)
-            infohub.policy_rejected_logps.append(policy_rejected_logps)
-            infohub.sft_loss.append(sft_loss)
-            infohub.dpo_loss.append(dpo_loss)
+            infohub.policy_chosen_logps.append(policy_chosen_logps.detach())
+            infohub.policy_rejected_logps.append(policy_rejected_logps.detach())
+            infohub.sft_loss.append(sft_loss.detach())
+            infohub.dpo_loss.append(dpo_loss.detach())
             return loss
         else:
             return policy_chosen_logps, policy_rejected_logps, sft_loss, dpo_loss, loss
diff --git a/paddlenlp/trl/kto_criterion.py b/paddlenlp/trl/kto_criterion.py
@@ -247,10 +247,10 @@ def forward(
             reference_kl_logps,
         )
         if self.use_infohub:
-            infohub.policy_chosen_logps.append(policy_chosen_logps)
-            infohub.policy_rejected_logps.append(policy_rejected_logps)
-            infohub.policy_kl_logps.append(policy_kl_logps)
-            infohub.kl.append(kl)
+            infohub.policy_chosen_logps.append(policy_chosen_logps.detach())
+            infohub.policy_rejected_logps.append(policy_rejected_logps.detach())
+            infohub.policy_kl_logps.append(policy_kl_logps.detach())
+            infohub.kl.append(kl.detach())
             return loss
         else:
             return (