diff --git a/python/paddle/distributed/fleet/model.py b/python/paddle/distributed/fleet/model.py
index e7cd0b33e9d16d2bebd064323d81bc66ca751786..c849a94dcea5d308c0fbe10835d05f6b0a44d710 100755
--- a/python/paddle/distributed/fleet/model.py
+++ b/python/paddle/distributed/fleet/model.py
@@ -41,44 +41,40 @@ def distributed_model(model):
 
         .. code-block:: python
 
-            import paddle
-            import paddle.nn as nn
-            from paddle.distributed import fleet
-
-            class LinearNet(nn.Layer):
-                def __init__(self):
-                    super().__init__()
-                    self._linear1 = nn.Linear(10, 10)
-                    self._linear2 = nn.Linear(10, 1)
-
-                def forward(self, x):
-                    return self._linear2(self._linear1(x))
-
-            # 1. initialize fleet environment
-            fleet.init(is_collective=True)
-
-            # 2. create layer & optimizer
-            layer = LinearNet()
-            loss_fn = nn.MSELoss()
-            adam = paddle.optimizer.Adam(
-                learning_rate=0.001, parameters=layer.parameters())
-
-            # 3. get data_parallel model using fleet
-            adam = fleet.distributed_optimizer(adam)
-            dp_layer = fleet.distributed_model(layer)
-
-            # 4. run layer
-            inputs = paddle.randn([10, 10], 'float32')
-            outputs = dp_layer(inputs)
-            labels = paddle.randn([10, 1], 'float32')
-            loss = loss_fn(outputs, labels)
-
-            print("loss:", loss.numpy())
-
-            loss.backward()
-
-            adam.step()
-            adam.clear_grad()
+            >>> import paddle
+            >>> import paddle.nn as nn
+            >>> from paddle.distributed import fleet
+
+            >>> class LinearNet(nn.Layer):
+            ...     def __init__(self):
+            ...         super().__init__()
+            ...         self._linear1 = nn.Linear(10, 10)
+            ...         self._linear2 = nn.Linear(10, 1)
+            ...     def forward(self, x):
+            ...         return self._linear2(self._linear1(x))
+
+            >>> # 1. initialize fleet environment
+            >>> fleet.init(is_collective=True)
+
+            >>> # 2. create layer & optimizer
+            >>> layer = LinearNet()
+            >>> loss_fn = nn.MSELoss()
+            >>> adam = paddle.optimizer.Adam(
+            ...     learning_rate=0.001, parameters=layer.parameters())
+
+            >>> # 3. get data_parallel model using fleet
+            >>> adam = fleet.distributed_optimizer(adam)
+            >>> dp_layer = fleet.distributed_model(layer)
+
+            >>> # 4. run layer
+            >>> inputs = paddle.randn([10, 10], 'float32')
+            >>> outputs = dp_layer(inputs)
+            >>> labels = paddle.randn([10, 1], 'float32')
+            >>> loss = loss_fn(outputs, labels)
+            >>> print("loss:", loss.numpy())
+            >>> loss.backward()
+            >>> adam.step()
+            >>> adam.clear_grad()
 
 
     """
diff --git a/python/paddle/distributed/fleet/optimizer.py b/python/paddle/distributed/fleet/optimizer.py
index 9e693e670f3ff2945a9d846a75d99f89ddd9ff61..85c27fd138ef311164844dcf32aa51ddfe66d51c 100755
--- a/python/paddle/distributed/fleet/optimizer.py
+++ b/python/paddle/distributed/fleet/optimizer.py
@@ -37,12 +37,15 @@ def _dygraph_distributed_optimizer(optimizer, strategy=None):
         Fleet: instance of fleet.
     Examples:
         .. code-block:: python
-            import paddle
-            import paddle.distributed.fleet as fleet
-            fleet.init(is_collective=True)
-            strategy = fleet.DistributedStrategy()
-            optimizer = paddle.optimizer.SGD(learning_rate=0.001)
-            optimizer = fleet.distributed_optimizer(optimizer, strategy=strategy)
+
+            >>> import paddle
+            >>> import paddle.distributed.fleet as fleet
+            >>> fleet.init(is_collective=True)
+            >>> strategy = fleet.DistributedStrategy()
+            >>> linear = paddle.nn.Linear(10, 10)
+            >>> optimizer = paddle.optimizer.SGD(learning_rate=0.001, parameters=linear.parameters())
+            >>> optimizer = fleet.distributed_optimizer(optimizer, strategy=strategy)
+
     """
     fleet_env = fleet.fleet
     fleet_env.user_defined_optimizer = optimizer