diff --git a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
index b07d5137f..bac0ac1a9 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
@@ -78,5 +78,6 @@ torchrun $DISTRIBUTED_ARGS \
 ++train_conf.avg_nbest_model=10 \
 ++train_conf.use_deepspeed=false \
 ++train_conf.deepspeed_config=${deepspeed_config} \
+++train_conf.find_unused_parameters=true \
 ++optim_conf.lr=0.0002 \
 ++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/funasr/bin/train_ds.py b/funasr/bin/train_ds.py
index 5b1eeaa9c..dc7fb4223 100644
--- a/funasr/bin/train_ds.py
+++ b/funasr/bin/train_ds.py
@@ -134,7 +134,7 @@ def main(**kwargs):
         **kwargs.get("train_conf"),
     )
 
-    model = trainer.warp_model(model)
+    model = trainer.warp_model(model, **kwargs)
 
     kwargs["device"] = int(os.environ.get("LOCAL_RANK", 0))
     trainer.device = int(os.environ.get("LOCAL_RANK", 0))