added pad_id use

Author: vlad-karp

src/maxtext/trainers/post_train/distillation/train_distill.py

@@ -463,6 +463,7 @@ def train_distill(
   strategy = distillation_utils.CombinedDistillationStrategy(
       student_forward_fn=student_forward_fn,
       teacher_forward_fn=teacher_forward_fn,
+      pad_id=pad_id,
       temperature=student_config.distill_temperature,
       alpha=student_config.distill_alpha,
       beta_feature=student_config.distill_beta,