diff --git a/tests/metrics/README.md b/tests/metrics/README.md
index d017ed3fc..d67904620 100644
--- a/tests/metrics/README.md
+++ b/tests/metrics/README.md
@@ -79,6 +79,8 @@ Test relating to measure reading and writing against clusters.
 Tests relating with TensorFlow and Pytorch implementations of several popular
 convolutional models.
 
+For further details see the [machine learning tests documentation](machine_learning).
+
 ## Saving Results
 
 In order to ensure continuity, and thus testing and historical tracking of results,
diff --git a/tests/metrics/machine_learning/README.md b/tests/metrics/machine_learning/README.md
new file mode 100644
index 000000000..8c62b1566
--- /dev/null
+++ b/tests/metrics/machine_learning/README.md
@@ -0,0 +1,29 @@
+# Kata Containers Tensorflow Metrics
+
+Kata Containers provides a series of performance tests using the
+TensorFlow reference benchmarks (tf_cnn_benchmarks).
+The tf_cnn_benchmarks containers TensorFlow implementations of several
+popular convolutional models.
+
+## Running the test
+
+Individual tests can be run by hand, for example:
+
+```
+$ cd metrics/machine_learning
+$ ./tensorflow.sh 25 60
+```
+# Kata Containers Pytorch Metrics
+
+Kata Containers provides a series of performance tests using Pytorch
+benchmarks based on a suite of Python high performance computing
+benchmarks.
+
+## Running the Pytorch test
+
+Individual tests can be run by hand, for example:
+
+```
+$ cd metrics/machine_learning
+$ ./tensorflow.sh 40 100
+```