diff --git a/tensorflow_probability/examples/jupyter_notebooks/Optimizers_in_TensorFlow_Probability.ipynb b/tensorflow_probability/examples/jupyter_notebooks/Optimizers_in_TensorFlow_Probability.ipynb
index c5c8081c25..a43455a009 100644
--- a/tensorflow_probability/examples/jupyter_notebooks/Optimizers_in_TensorFlow_Probability.ipynb
+++ b/tensorflow_probability/examples/jupyter_notebooks/Optimizers_in_TensorFlow_Probability.ipynb
@@ -242,7 +242,7 @@
         "# starting point.\n",
         "start = np.random.randn(dim)\n",
         "\n",
-        "# Finally an optional argument called tolerance let's you choose the\n",
+        "# Finally an optional argument called tolerance lets you choose the\n",
         "# stopping point of the search. The tolerance specifies the maximum\n",
         "# (supremum) norm of the gradient vector at which the algorithm terminates.\n",
         "# If you don't have a specific need for higher or lower accuracy, leaving\n",