diff --git a/fastNLP/core/losses.py b/fastNLP/core/losses.py
index 9b8b8d8f..b52244e5 100644
--- a/fastNLP/core/losses.py
+++ b/fastNLP/core/losses.py
@@ -251,7 +251,8 @@ class LossInForward(LossBase):
         if not (isinstance(loss, torch.Tensor) and len(loss.size()) == 0):
             if not isinstance(loss, torch.Tensor):
                 raise TypeError(f"Loss excepted to be a torch.Tensor, got {type(loss)}")
-            raise RuntimeError(f"The size of loss excepts to be torch.Size([]), got {loss.size()}")
+            loss = torch.sum(loss) / (loss.view(-1)).size(0)
+            # raise RuntimeError(f"The size of loss excepts to be torch.Size([]), got {loss.size()}")
 
         return loss
 
diff --git a/fastNLP/modules/decoder/MLP.py b/fastNLP/modules/decoder/MLP.py
index d75f6b48..3a793f24 100644
--- a/fastNLP/modules/decoder/MLP.py
+++ b/fastNLP/modules/decoder/MLP.py
@@ -36,6 +36,7 @@ class MLP(nn.Module):
         actives = {
             'relu': nn.ReLU(),
             'tanh': nn.Tanh(),
+            'sigmoid': nn.Sigmoid(),
         }
         if not isinstance(activation, list):
             activation = [activation] * (len(size_layer) - 2)
diff --git a/reproduction/README.md b/reproduction/README.md
index 1c93c6bc..8d14d36d 100644
--- a/reproduction/README.md
+++ b/reproduction/README.md
@@ -8,7 +8,7 @@
 
 ## Star-Transformer
 [reference](https://arxiv.org/abs/1902.09113)
-### Performance
+### Performance (still in progress)
 |任务| 数据集 | SOTA | 模型表现 |
 |------|------| ------| ------|
 |Pos Tagging|CTB 9.0|-|ACC 92.31|