diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 00000000..df42280a
Binary files /dev/null and b/.DS_Store differ
diff --git a/pytorch/.DS_Store b/pytorch/.DS_Store
new file mode 100644
index 00000000..16d967e9
Binary files /dev/null and b/pytorch/.DS_Store differ
diff --git a/pytorch/nlp/evaluate.py b/pytorch/nlp/evaluate.py
index f0b0fe0a..beeb5019 100644
--- a/pytorch/nlp/evaluate.py
+++ b/pytorch/nlp/evaluate.py
@@ -51,7 +51,7 @@ def evaluate(model, loss_fn, data_iterator, metrics, params, num_steps):
         # compute all metrics on this batch
         summary_batch = {metric: metrics[metric](output_batch, labels_batch)
                          for metric in metrics}
-        summary_batch['loss'] = loss.data[0]
+        summary_batch['loss'] = loss.item()
         summ.append(summary_batch)
 
     # compute mean of all metrics in summary
diff --git a/pytorch/nlp/train.py b/pytorch/nlp/train.py
index 8ef8c54a..d5789fec 100644
--- a/pytorch/nlp/train.py
+++ b/pytorch/nlp/train.py
@@ -69,11 +69,11 @@ def train(model, optimizer, loss_fn, data_iterator, metrics, params, num_steps):
             # compute all metrics on this batch
             summary_batch = {metric:metrics[metric](output_batch, labels_batch)
                              for metric in metrics}
-            summary_batch['loss'] = loss.data[0]
+            summary_batch['loss'] = loss.item()
             summ.append(summary_batch)
 
         # update the average loss
-        loss_avg.update(loss.data[0])
+        loss_avg.update(loss.item())
         t.set_postfix(loss='{:05.3f}'.format(loss_avg()))
 
     # compute mean of all metrics in summary
diff --git a/pytorch/vision/evaluate.py b/pytorch/vision/evaluate.py
index ddd84dbb..5a850ce8 100644
--- a/pytorch/vision/evaluate.py
+++ b/pytorch/vision/evaluate.py
@@ -56,7 +56,7 @@ def evaluate(model, loss_fn, dataloader, metrics, params):
         # compute all metrics on this batch
         summary_batch = {metric: metrics[metric](output_batch, labels_batch)
                          for metric in metrics}
-        summary_batch['loss'] = loss.data[0]
+        summary_batch['loss'] = loss.item()
         summ.append(summary_batch)
 
     # compute mean of all metrics in summary
diff --git a/pytorch/vision/train.py b/pytorch/vision/train.py
index ded5554e..2779d4f9 100644
--- a/pytorch/vision/train.py
+++ b/pytorch/vision/train.py
@@ -72,11 +72,11 @@ def train(model, optimizer, loss_fn, dataloader, metrics, params):
                 # compute all metrics on this batch
                 summary_batch = {metric:metrics[metric](output_batch, labels_batch)
                                  for metric in metrics}
-                summary_batch['loss'] = loss.data[0]
+                summary_batch['loss'] = loss.item()
                 summ.append(summary_batch)
 
             # update the average loss
-            loss_avg.update(loss.data[0])
+            loss_avg.update(loss.item())
 
             t.set_postfix(loss='{:05.3f}'.format(loss_avg()))
             t.update()