Update torch_compile_tutorial.py

Author: Svetlana Karslioglu

intermediate_source/torch_compile_tutorial.py

@@ -233,7 +233,7 @@ def train(mod, data):
 
 ######################################################################
 # Again, we can see that ``torch.compile`` takes longer in the first
-# iteration, as it must compile the model, but afterward, we see
+# iteration, as it must compile the model, but in subsequent iterations, we see
 # significant speedups compared to eager. On an NVIDIA A100 GPU, we
 # observe a ~1.8x speedup.
 
@@ -493,4 +493,4 @@ def bar(a, b):
 # In this tutorial, we introduced ``torch.compile`` by covering
 # basic usage, demonstrating speedups over eager mode, comparing to previous
 # PyTorch compiler solutions, and briefly investigating TorchDynamo and its interactions
-# with FX graphs. We hope that you will give ``torch.compile`` a try!
+# with FX graphs. We hope that you will give ``torch.compile`` a try!