diff --git a/pytorch_lightning/models/trainer.py b/pytorch_lightning/models/trainer.py
index dcf100b0..9af112c5 100644
--- a/pytorch_lightning/models/trainer.py
+++ b/pytorch_lightning/models/trainer.py
@@ -29,9 +29,6 @@ def reduce_distributed_output(output, nb_gpus):
             output[k] = reduced
     return output
 
-def dummy(gpu, a):
-    print(a)
-
 class Trainer(TrainerIO):
 
     def __init__(self,
diff --git a/pytorch_lightning/pt_overrides/override_data_parallel.py b/pytorch_lightning/pt_overrides/override_data_parallel.py
index 18bc4162..cf4f476e 100644
--- a/pytorch_lightning/pt_overrides/override_data_parallel.py
+++ b/pytorch_lightning/pt_overrides/override_data_parallel.py
@@ -28,7 +28,6 @@ class LightningDataParallel(DataParallel):
     """
 
     def parallel_apply(self, replicas, inputs, kwargs):
-        print('parallel_apply called')
         return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])