diff --git a/PaddleRec/din/data/data_process.sh b/PaddleRec/din/data/data_process.sh
index 93b1c32d68ec40a9eb7b85ffaa896ea4a5e8052f..7bcfc55f43119315d543e06f16fe0ebc0fecb9fc 100644
--- a/PaddleRec/din/data/data_process.sh
+++ b/PaddleRec/din/data/data_process.sh
@@ -1,12 +1,14 @@
 #! /bin/bash
 
+set -e
 echo "begin download data"
-mkdir raw_data && cd raw_data
+mkdir raw_data
+cd raw_data
 wget -c http://snap.stanford.edu/data/amazon/productGraph/categoryFiles/reviews_Electronics_5.json.gz
 gzip -d reviews_Electronics_5.json.gz
 wget -c http://snap.stanford.edu/data/amazon/productGraph/categoryFiles/meta_Electronics.json.gz
 gzip -d meta_Electronics.json.gz
-echo "download data successful"
+echo "download data successfully"
 
 cd ..
 python convert_pd.py
diff --git a/PaddleRec/din/train.py b/PaddleRec/din/train.py
index 36e99580e8b66c8347b3e791c20c2de514c87dce..dbf0e77efdbd2aed6ea06c8e0f2f42904807b11a 100644
--- a/PaddleRec/din/train.py
+++ b/PaddleRec/din/train.py
@@ -136,7 +136,7 @@ def train():
 
                 if (global_step > 400000 and global_step % PRINT_STEP == 0) or (
                         global_step <= 400000 and global_step % 50000 == 0):
-                    save_dir = os.path.join(args.model_dir, "/global_step_" + str(
+                    save_dir = os.path.join(args.model_dir, "global_step_" + str(
                         global_step))
                     feed_var_name = [
                         "hist_item_seq", "hist_cat_seq", "target_item",