diff --git a/pytorch_widedeep/callbacks.py b/pytorch_widedeep/callbacks.py
index b0adafd069d9b78a968efb4295e4807b3d9bafb1..b76b887eeb8328bccc5572ce95dce616944c4cc4 100644
--- a/pytorch_widedeep/callbacks.py
+++ b/pytorch_widedeep/callbacks.py
@@ -498,7 +498,7 @@ class ModelCheckpoint(Callback):
                                     )
                                 )
                         if self.wb is not None:
-                            self.wb.run.summary["best"] = current
+                            self.wb.run.summary["best"] = current  # type: ignore[attr-defined]
                         self.best = current
                         self.best_epoch = epoch
                         self.best_state_dict = self.model.state_dict()
diff --git a/pytorch_widedeep/datasets/__init__.py b/pytorch_widedeep/datasets/__init__.py
index 9eb2d2c41d09bf59a14d4fe1b6efc1349d1b4ae0..b4ba41cbc4028a92610058ac32b9d3bf3a94ba5f 100644
--- a/pytorch_widedeep/datasets/__init__.py
+++ b/pytorch_widedeep/datasets/__init__.py
@@ -1,3 +1,3 @@
-from ._base import load_bio_kdd04, load_adult
+from ._base import load_adult, load_bio_kdd04
 
 __all__ = ["load_bio_kdd04", "load_adult"]
diff --git a/pytorch_widedeep/datasets/_base.py b/pytorch_widedeep/datasets/_base.py
index 78bf97c7f38dc2fc3bbd7418c4fe5d74ac735273..45e3e76a488b44069c16c5a1042dc444506ec984 100644
--- a/pytorch_widedeep/datasets/_base.py
+++ b/pytorch_widedeep/datasets/_base.py
@@ -1,4 +1,5 @@
 from importlib import resources
+
 import pandas as pd
 
 
diff --git a/pytorch_widedeep/models/transformers/_embeddings_layers.py b/pytorch_widedeep/models/transformers/_embeddings_layers.py
index 51c54890feea4d263daf4eeb3861d07bfa2c5288..5d3415812119dbe22357c9baf8db150a3d37c546 100644
--- a/pytorch_widedeep/models/transformers/_embeddings_layers.py
+++ b/pytorch_widedeep/models/transformers/_embeddings_layers.py
@@ -4,6 +4,7 @@ https://github.com/awslabs/autogluon/tree/master/tabular/src/autogluon/tabular/m
 """
 
 import math
+import warnings
 
 import torch
 from torch import nn
@@ -19,9 +20,9 @@ class FullEmbeddingDropout(nn.Module):
 
     def forward(self, X: Tensor) -> Tensor:
         if self.training:
-            mask = X.new().resize_((X.size(1), 1)).bernoulli_(1 - self.dropout).expand_as(
-                X
-            ) / (1 - self.dropout)
+            mask = X.new().resize_((X.size(1), 1)).bernoulli_(
+                1 - self.dropout
+            ).expand_as(X) / (1 - self.dropout)
             return mask * X
         else:
             return X
@@ -128,13 +129,16 @@ class CategoricalEmbeddings(nn.Module):
         self.categorical_cols = [ei[0] for ei in embed_input]
         self.cat_idx = [self.column_idx[col] for col in self.categorical_cols]
 
-        self.bias = (
-            nn.Parameter(torch.Tensor(len(self.categorical_cols), embed_dim))
-            if use_bias
-            else None
-        )
-        if self.bias is not None:
+        if use_bias is not None:
+            self.bias = nn.Parameter(
+                torch.Tensor(len(self.categorical_cols), embed_dim)
+            )
             nn.init.kaiming_uniform_(self.bias, a=math.sqrt(5))
+            if shared_embed:
+                warnings.warn(
+                    "The current implementation of 'SharedEmbeddings' does not use bias",
+                    UserWarning,
+                )
 
         # Categorical: val + 1 because 0 is reserved for padding/unseen cateogories.
         if self.shared_embed:
@@ -170,11 +174,11 @@ class CategoricalEmbeddings(nn.Module):
             x = torch.cat(cat_embed, 1)
         else:
             x = self.embed(X[:, self.cat_idx].long())
+            if self.bias is not None:
+                x = x + self.bias.unsqueeze(0)
+            x = self.dropout(x)
 
-        if self.bias is not None:
-            x = x + self.bias.unsqueeze(0)
-
-        return self.dropout(x)
+        return x
 
 
 class CatAndContEmbeddings(nn.Module):
diff --git a/tests/test_datasets/test_datasets.py b/tests/test_datasets/test_datasets.py
index 01b35fbe8d703e20230bc17d98b823022212f4f9..acfca3c231fd2cd615adef0518f469043ecd6ef3 100644
--- a/tests/test_datasets/test_datasets.py
+++ b/tests/test_datasets/test_datasets.py
@@ -1,8 +1,9 @@
-from pytorch_widedeep.datasets import load_bio_kdd04, load_adult
-import pandas as pd
 import numpy as np
+import pandas as pd
 import pytest
 
+from pytorch_widedeep.datasets import load_adult, load_bio_kdd04
+
 
 @pytest.mark.parametrize(
     "as_frame",