diff --git a/examples/seq2seq/test_finetune_trainer.py b/examples/seq2seq/test_finetune_trainer.py
index e8f7d431b6c..94904629713 100644
--- a/examples/seq2seq/test_finetune_trainer.py
+++ b/examples/seq2seq/test_finetune_trainer.py
@@ -153,7 +153,7 @@ class TestFinetuneTrainer(TestCasePlus):
             --save_steps {str(eval_steps)}
             --eval_steps {str(eval_steps)}
             --sortish_sampler
-            --label_smoothing 0.1
+            --label_smoothing_factor 0.1
             --adafactor
             --task translation
             --tgt_lang ro_RO
diff --git a/examples/seq2seq/train_distil_marian_enro.sh b/examples/seq2seq/train_distil_marian_enro.sh
index 82f7725003e..fc1b90595c5 100644
--- a/examples/seq2seq/train_distil_marian_enro.sh
+++ b/examples/seq2seq/train_distil_marian_enro.sh
@@ -34,5 +34,5 @@ python finetune_trainer.py \
     --do_train --do_eval --do_predict \
     --evaluation_strategy steps \
     --predict_with_generate --logging_first_step \
-    --task translation --label_smoothing 0.1 \
+    --task translation --label_smoothing_factor 0.1 \
     "$@"
diff --git a/examples/seq2seq/train_distil_marian_enro_tpu.sh b/examples/seq2seq/train_distil_marian_enro_tpu.sh
index 82f6ce1406e..2fce7684ab4 100644
--- a/examples/seq2seq/train_distil_marian_enro_tpu.sh
+++ b/examples/seq2seq/train_distil_marian_enro_tpu.sh
@@ -35,5 +35,5 @@ python xla_spawn.py --num_cores $TPU_NUM_CORES \
     --do_train --do_eval \
     --evaluation_strategy steps \
     --prediction_loss_only \
-    --task translation --label_smoothing 0.1 \
+    --task translation --label_smoothing_factor 0.1 \
     "$@"