Merge pull request #99 from awslabs/nolliag-tf-abalone-keras-patch

Correct some minor grammatical issues.

Author: mvsusp

sagemaker-python-sdk/tensorflow_abalone_age_predictor_using_keras/tensorflow_abalone_age_predictor_using_keras.ipynb

@@ -123,7 +123,7 @@
    "source": [
     "## Defining a `model_fn`\n",
     "\n",
-    "The script above implements a `model_fn` as the function resposible for implementing the model for training, evaluation, and prediction. The next section covers how to implement a `model_fn` using `Keras layers`. \n",
+    "The script above implements a `model_fn` as the function responsible for implementing the model for training, evaluation, and prediction. The next section covers how to implement a `model_fn` using `Keras layers`. \n",
     "\n",
     "\n",
     "\n",
@@ -164,7 +164,7 @@
     "The body of the function performs the following tasks (described in detail in the\n",
     "sections that follow):\n",
     "\n",
-    "*   Configuring the model for the abalone predictor, this will be a neural\n",
+    "*   Configuring the model for the abalone predictor. This will be a neural\n",
     "    network.\n",
     "*   Defining the loss function used to calculate how closely the model's\n",
     "    predictions match the target values.\n",
@@ -474,7 +474,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "`estimator.fit` will deploy a script in a container for training and returs the SageMaker model name using the following arguments:\n",
+    "`estimator.fit` will deploy a script in a container for training and returns the SageMaker model name using the following arguments:\n",
     "\n",
     "*   **`entry_point=\"abalone.py\"`** The path to the script that will be deployed to the container.\n",
     "*   **`training_steps=100`** The number of training steps of the training job.\n",
@@ -587,4 +587,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}