diff --git a/src/transformers/models/bert/configuration_bert.py b/src/transformers/models/bert/configuration_bert.py
index 25c0f5b67ef..b3dfcdff75e 100644
--- a/src/transformers/models/bert/configuration_bert.py
+++ b/src/transformers/models/bert/configuration_bert.py
@@ -123,12 +123,12 @@ class BertConfig(PretrainedConfig):
     Examples:
 
     ```python
-    >>> from transformers import BertModel, BertConfig
+    >>> from transformers import BertConfig, BertModel
 
     >>> # Initializing a BERT bert-base-uncased style configuration
     >>> configuration = BertConfig()
 
-    >>> # Initializing a model from the bert-base-uncased style configuration
+    >>> # Initializing a model (with random weights) from the bert-base-uncased style configuration
     >>> model = BertModel(configuration)
 
     >>> # Accessing the model configuration
diff --git a/utils/documentation_tests.txt b/utils/documentation_tests.txt
index a39dc7a56a8..769b7ca0982 100644
--- a/utils/documentation_tests.txt
+++ b/utils/documentation_tests.txt
@@ -16,6 +16,7 @@ src/transformers/models/albert/modeling_albert.py
 src/transformers/models/albert/modeling_tf_albert.py
 src/transformers/models/bart/modeling_bart.py
 src/transformers/models/beit/modeling_beit.py
+src/transformers/models/bert/configuration_bert.py
 src/transformers/models/bert/modeling_bert.py
 src/transformers/models/bert/modeling_tf_bert.py
 src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py