diff --git a/src/transformers/models/albert/configuration_albert.py b/src/transformers/models/albert/configuration_albert.py
index fd0c6238879..cacc0499035 100644
--- a/src/transformers/models/albert/configuration_albert.py
+++ b/src/transformers/models/albert/configuration_albert.py
@@ -85,6 +85,12 @@ class AlbertConfig(PretrainedConfig):
             [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
             For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
             with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
+        pad_token_id (`int`, *optional*, defaults to 0):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 2):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 3):
+            End of stream token id.
 
     Examples:
 
diff --git a/utils/check_docstrings.py b/utils/check_docstrings.py
index 8d69ea603f1..650b519eaa5 100644
--- a/utils/check_docstrings.py
+++ b/utils/check_docstrings.py
@@ -75,7 +75,6 @@ OBJECTS_TO_IGNORE = [
     "TFGPT2Tokenizer",
     # Missing arguments in the docstring
     "ASTFeatureExtractor",
-    "AlbertConfig",
     "AlbertModel",
     "AlbertTokenizerFast",
     "AlignTextModel",