...

README.md

@@ -2,12 +2,10 @@
 
 This project is part of the [Machine Learning School](https://www.ml.school) program.
 
-* The [Penguins in Production](penguins.ipynb) notebook: An Amazon SageMaker pipeline hosting a multi-class classification model for the [Penguins dataset](https://www.kaggle.com/parulpandey/palmer-archipelago-antarctica-penguin-data).
+* The [Penguins in Production](penguins-cohort.ipynb) notebook: An Amazon SageMaker pipeline hosting a multi-class classification model for the [Penguins dataset](https://www.kaggle.com/parulpandey/palmer-archipelago-antarctica-penguin-data).
 * The [Pipeline of Digits](mnist/mnist.ipynb) notebook: A starting notebook for solving the "Pipeline of Digits" assignment.
 
-## Session 1 - Getting Started
-
-This session aims to build a simple [SageMaker Pipeline](https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-sdk.html) with one step to preprocess the [Penguins dataset](https://www.kaggle.com/parulpandey/palmer-archipelago-antarctica-penguin-data). We'll use a [Processing Step](https://docs.aws.amazon.com/sagemaker/latest/dg/build-and-manage-steps.html#step-type-processing) with a [SKLearnProcessor](https://sagemaker.readthedocs.io/en/stable/frameworks/sklearn/sagemaker.sklearn.html#scikit-learn-processor) to execute a preprocessing script. Check the [SageMaker Pipelines Overview](https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-sdk.html) for an introduction to the fundamental components of a SageMaker Pipeline.
+## Session 1 - Preprocessing the Data
 
 ### Assignments
 
@@ -32,8 +30,6 @@ $ git config --global credential.helper store
 
 ## Session 2 - Model Training and Tuning
 
-This session extends the [SageMaker Pipeline](https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-sdk.html) we built in the previous session with a step to train a model. We'll explore the [Training](https://docs.aws.amazon.com/sagemaker/latest/dg/build-and-manage-steps.html#step-type-training) and the [Tuning](https://docs.aws.amazon.com/sagemaker/latest/dg/build-and-manage-steps.html#step-type-tuning) steps. 
-
 ### Assignments
 
 1. Modify the training script to accept the `learning_rate` as a new hyperparameter. You can use the list of hyperparameters supplied to the Estimator.
@@ -45,9 +41,7 @@ This session extends the [SageMaker Pipeline](https://docs.aws.amazon.com/sagema
 4. Modify the SageMaker Pipeline you created for the "Pipeline of Digits" project and add a Training Step. This Training Step should receive the training and validation data from the Processing Step you created in Session 1.
 
 
-## Session 3 - Model Evaluation
-
-This session extends the [SageMaker Pipeline](https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-sdk.html) with a step to evaluate the model. We'll use a [Processing Step](https://docs.aws.amazon.com/sagemaker/latest/dg/build-and-manage-steps.html#step-type-processing) with a [ScriptProcessor](https://sagemaker.readthedocs.io/en/stable/api/training/processing.html#sagemaker.processing.ScriptProcessor) running TensorFlow to execute an evaluation script. 
+## Session 3 - Model Evaluation and Registration
 
 ### Assignments