Fix typo in MNIST tutorials

docs/tutorials/mnist.ipynb

@@ -180,7 +180,7 @@
     "\n",
     "- Loads the raw data from Keras.\n",
     "- Filters the dataset to only 3s and 6s.\n",
-    "- Downscales the images so they fit can fit in a quantum computer.\n",
+    "- Downscales the images so they can fit in a quantum computer.\n",
     "- Removes any contradictory examples.\n",
     "- Converts the binary images to Cirq circuits.\n",
     "- Converts the Cirq circuits to TensorFlow Quantum circuits. "
@@ -784,7 +784,7 @@
    "source": [
     "Next, describe the training procedure to the model, using the `compile` method.\n",
     "\n",
-    "Since the the expected readout is in the range `[-1,1]`, optimizing the hinge loss is a somewhat natural fit. \n",
+    "Since the expected readout is in the range `[-1,1]`, optimizing the hinge loss is a somewhat natural fit. \n",
     "\n",
     "Note: Another valid approach would be to shift the output range to `[0,1]`, and treat it as the probability the model assigns to class `3`. This could be used with a standard a `tf.losses.BinaryCrossentropy` loss.\n",
     "\n",
@@ -812,7 +812,7 @@
     "id": "5nwnveDiojh7"
    },
    "source": [
-    "Second, use a custiom `hinge_accuracy` metric that correctly handles `[-1, 1]` as the `y_true` labels argument. \n",
+    "Second, use a custom `hinge_accuracy` metric that correctly handles `[-1, 1]` as the `y_true` labels argument. \n",
     "`tf.losses.BinaryAccuracy(threshold=0.0)` expects `y_true` to be a boolean, and so can't be used with hinge loss)."
    ]
   },
@@ -926,7 +926,7 @@
    "source": [
     "qnn_history = model.fit(x_train_tfcirc_sub,\n",
     "                        y_train_hinge_sub,\n",
-    "                        batch_size=32,\n",
+    "                        batch_size=BATCH_SIZE,\n",
     "                        epochs=EPOCHS,\n",
     "                        verbose=1,\n",
     "                        validation_data=(x_test_tfcirc, y_test_hinge))\n",