diff --git a/python/paddle/hapi/model.py b/python/paddle/hapi/model.py
index fa8bd600bb28d8e99f5fbeed54db754274e592bf..6cd879c388c1f6f8d5914e144841e8678119cb45 100644
--- a/python/paddle/hapi/model.py
+++ b/python/paddle/hapi/model.py
@@ -887,10 +887,10 @@ class Model(object):
     AdamW and Momentum optimizer. Before using pure float16 training,
     `multi_precision` could be set to True when creating optimizer, which can
     avoid poor accuracy or slow convergence in a way, and inputs of dtype float
-    should be cast to float16 by users. Users should also use
-    `paddle.static.amp.fp16_guard` API to limit the range of pure float16
-    training, otherwise, 'use_fp16_guard' should be set to False by users.
-    However, limiting the range of is not supported during training using AMP.
+    should be cast to float16 by users. `paddle.static.amp.fp16_guard` API
+    should be also used to limit the range of pure float16 training, otherwise,
+    'use_fp16_guard' should be set to False by users. However, limiting the
+    range of is not supported during training using AMP.
 
     Args:
         network (paddle.nn.Layer): The network is an instance of
@@ -974,7 +974,7 @@ class Model(object):
             data = paddle.vision.datasets.MNIST(mode='train', transform=transform)
             model.fit(data, epochs=2, batch_size=32, verbose=1)
 
-          # mixed precision training is only support on GPU now.
+          # mixed precision training is only supported on GPU now.
           if paddle.is_compiled_with_cuda():
             run_example_code()
 
@@ -1462,19 +1462,18 @@ class Model(object):
                 float16 training is used, the key 'level' of 'amp_configs'
                 should be set to 'O1' or 'O2' respectively. Otherwise, the
                 value of 'level' defaults to 'O0', which means float32
-                training. In addition to 'level', users could pass in more
-                parameters consistent with mixed precision API. The supported
+                training. In addition to 'level', parameters consistent with
+                mixed precision API could also be passed in. The supported
                 keys are: 'init_loss_scaling', 'incr_ratio', 'decr_ratio',
                 'incr_every_n_steps', 'decr_every_n_nan_or_inf',
                 'use_dynamic_loss_scaling', 'custom_white_list',
                 'custom_black_list', and 'custom_black_varnames'or
-                'use_fp16_guard' is only supported in static mode. Users could
-                refer to mixed precision API documentations
-                 :ref:`api_paddle_amp_auto_cast` and
-                 :ref:`api_paddle_amp_GradScaler` for details. For convenience,
-                'amp_configs' could be set to 'O1' or 'O2' if no more
-                parameters are needed. 'amp_configs' could be None in float32
-                training. Default: None.
+                'use_fp16_guard' is only supported in static mode. Mixed
+                precision API documentations  :ref:`api_paddle_amp_auto_cast`
+                and  :ref:`api_paddle_amp_GradScaler` could be referenced
+                for details. For convenience, 'amp_configs' could be set to
+                'O1' or 'O2' if no more parameters are needed. 'amp_configs'
+                could be None in float32 training. Default: None.
         Returns:
             None
         """
diff --git a/python/paddle/metric/metrics.py b/python/paddle/metric/metrics.py
index 0784775b6695eefb091bf0643a0b5c12d4b4664f..b939f548e9c01d7be836a321a876d2abac7b74e4 100644
--- a/python/paddle/metric/metrics.py
+++ b/python/paddle/metric/metrics.py
@@ -243,7 +243,7 @@ class Accuracy(Metric):
 
     def compute(self, pred, label, *args):
         """
-        Compute the top-k (maxinum value in `topk`) indices.
+        Compute the top-k (maximum value in `topk`) indices.
 
         Args:
             pred (Tensor): The predicted value is a Tensor with dtype
@@ -253,7 +253,7 @@ class Accuracy(Metric):
                 [batch_size, d0, ..., num_classes] in one hot representation.
                 
         Return:
-            Tensor: Correct mask, a tensor with shape [batch_size, topk].
+            Tensor: Correct mask, a tensor with shape [batch_size, d0, ..., topk].
         """
         pred = paddle.argsort(pred, descending=True)
         pred = paddle.slice(
@@ -277,7 +277,7 @@ class Accuracy(Metric):
         returns the accuracy of current step.
         
         Args:
-            correct: Correct mask, a tensor with shape [batch_size, topk].
+            correct: Correct mask, a tensor with shape [batch_size, d0, ..., topk].
 
         Return:
             Tensor: the accuracy of current step.