@@ -263,7 +263,7 @@ server.
 $>mkdir /tmp/monitored
 $>cp -r /tmp/mnist_model/1 /tmp/monitored
 $>bazel build //tensorflow_serving/model_servers:tensorflow_model_server
-$>bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --enable_batching --port=9000 --model_name=mnist --model_base_path=/tmp/monitored --logtostderr
+$>bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --enable_batching --port=9000 --model_name=mnist --model_base_path=/tmp/monitored
 ~~~
 
 The server will emit log messages every one second that say
 
@@ -144,7 +144,7 @@ With that, your TensorFlow model is exported and ready to be loaded!
 
 ~~~shell
 $>bazel build //tensorflow_serving/model_servers:tensorflow_model_server
-$>bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=mnist --model_base_path=/tmp/mnist_model/ --logtostderr
+$>bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=mnist --model_base_path=/tmp/mnist_model/
 ~~~
 
 ## Test The Server
 
@@ -41,7 +41,6 @@ limitations under the License.
 // To specify model name (default "default"): --model_name=my_name
 // To specify port (default 8500): --port=my_port
 // To enable batching (default disabled): --enable_batching
-// To log on stderr (default disabled): --alsologtostderr
 
 #include <unistd.h>
 #include <iostream>
 
@@ -77,7 +77,6 @@ def RunServer(self, port, model_name, model_path, use_saved_model,
     command += ' --model_base_path=' + model_path
     command += ' --use_saved_model=' + str(use_saved_model).lower()
     command += ' --enable_batching=' + str(enable_batching).lower()
-    command += ' --alsologtostderr'
     print command
     self.server_proc = subprocess.Popen(shlex.split(command))
     print 'Server started'