diff --git a/mindspore/nn/optim/adam.py b/mindspore/nn/optim/adam.py
index ad7096a93f..b823bf69f3 100755
--- a/mindspore/nn/optim/adam.py
+++ b/mindspore/nn/optim/adam.py
@@ -398,8 +398,6 @@ class AdamWeightDecay(Optimizer):
         eps (float): Term added to the denominator to improve numerical stability. Default: 1e-6.
             Should be greater than 0.
         weight_decay (float): Weight decay (L2 penalty). It should be in range [0.0, 1.0]. Default: 0.0.
-        decay_filter (Function): A function to determine whether to apply weight decay on parameters. Default:
-                                 lambda x: 'LayerNorm' not in x.name and 'bias' not in x.name.
 
     Inputs:
         - **gradients** (tuple[Tensor]) - The gradients of `params`, the shape is the same as `params`.
diff --git a/mindspore/nn/optim/lamb.py b/mindspore/nn/optim/lamb.py
index d80facfbb1..0d2552b8c1 100755
--- a/mindspore/nn/optim/lamb.py
+++ b/mindspore/nn/optim/lamb.py
@@ -228,8 +228,6 @@ class Lamb(Optimizer):
         eps (float): Term added to the denominator to improve numerical stability. Default: 1e-6.
             Should be greater than 0.
         weight_decay (float): Weight decay (L2 penalty). Default: 0.0. Should be in range [0.0, 1.0].
-        decay_filter (Function): A function to determine whether to apply weight decay on parameters. Default:
-            lambda x: 'LayerNorm' not in x.name and 'bias' not in x.name.
 
     Inputs:
         - **gradients** (tuple[Tensor]) - The gradients of `params`, the shape is the same as `params`.