diff --git a/mindspore/nn/optim/ftrl.py b/mindspore/nn/optim/ftrl.py
index 15051c22c0..098c382da2 100644
--- a/mindspore/nn/optim/ftrl.py
+++ b/mindspore/nn/optim/ftrl.py
@@ -144,7 +144,7 @@ class FTRL(Optimizer):
         l2 (float): l2 regularization strength, must be greater than or equal to zero. Default: 0.0.
         use_locking (bool): If True use locks for update operation. Default: False.
         loss_scale (float): Value for the loss scale. It should be equal to or greater than 1.0. Default: 1.0.
-        wegith_decay (float): Weight decay value to multiply weight, should be in range [0.0, 1.0]. Default: 0.0.
+        weight_decay (float): Weight decay value to multiply weight, should be in range [0.0, 1.0]. Default: 0.0.
 
     Inputs:
         - **grads** (tuple[Tensor]) - The gradients of `params` in optimizer, the shape is as same as the `params`
diff --git a/mindspore/nn/optim/proximal_ada_grad.py b/mindspore/nn/optim/proximal_ada_grad.py
index 616f070d32..4fcca24764 100644
--- a/mindspore/nn/optim/proximal_ada_grad.py
+++ b/mindspore/nn/optim/proximal_ada_grad.py
@@ -99,7 +99,7 @@ class ProximalAdagrad(Optimizer):
         l2 (float): l2 regularization strength, must be greater than or equal to zero. Default: 0.0.
         use_locking (bool): If True use locks for update operation. Default: False.
         loss_scale (float): Value for the loss scale. It should be not less than 1.0. Default: 1.0.
-        wegith_decay (float): Weight decay value to multiply weight, should be in range [0.0, 1.0]. Default: 0.0.
+        weight_decay (float): Weight decay value to multiply weight, should be in range [0.0, 1.0]. Default: 0.0.
 
     Inputs:
         - **grads** (tuple[Tensor]) - The gradients of `params` in optimizer, the shape is as same as the `params`