Typo fix

Author: Yuval Fernbach

1_Monitoring_your_TensorFlow_scripts.ipynb

@@ -21,14 +21,18 @@
     "## Defining Training Metrics (Amazon SageMaker Python SDK)\n",
     "Define the metrics that you want to send to CloudWatch by specifying a list of metric names and regular expressions as the metric_definitions argument when you initialize an Estimator object. For example, if you want to monitor both the train:error and validation:error metrics in CloudWatch, your Estimator initialization would look like the following:\n",
     "```python \n",
-    "estimator = Estimator(image_name=ImageName,\n",
-    "            role='SageMakerRole', train_instance_count=1,\n",
-    "            train_instance_type='ml.c4.xlarge',            \n",
-    "            k=10,\n",
-    "            metric_definitions=[\n",
-    "                   {'Name': 'train:error', 'Regex': 'Train_error=(.*?);'},\n",
-    "                   {'Name': 'validation:error', 'Regex': 'Valid_error=(.*?);'}\n",
-    "            ])\n",
+    "estimator = TensorFlow(base_job_name='cifar10',\n",
+    "                       entry_point='cifar10_keras_sm.py',\n",
+    "                       source_dir='training_script',\n",
+    "                       role=role,\n",
+    "                       framework_version='1.12.0',\n",
+    "                       py_version='py3',\n",
+    "                       metric_definitions=[\n",
+    "                               {'Name': 'train:error', 'Regex': 'Train_error=(.*?);'},\n",
+    "                               {'Name': 'validation:error', 'Regex': 'Valid_error=(.*?);'}\n",
+    "                        ],\n",
+    "                       hyperparameters={'epochs' : 20},\n",
+    "                       train_instance_count=1, train_instance_type='ml.p3.2xlarge')\n",
     "```"
    ]
   },
@@ -60,7 +64,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Run the previous job, this time. add the ```metric_definitions=metric_definitions``` argument.  \n",
+    "Continue with the notebook and run the same job as before (Same estimator configuration).  this time, add the ```metric_definitions=metric_definitions``` argument.  \n",
     "Run the job for 20 epochs"
    ]
   },