TF ALBERT + TF Utilities + Fix warnings

docs/source/main_classes/optimizer_schedules.rst

@@ -20,14 +20,12 @@ The ``.optimization`` module provides:
     :members:
 
 .. autofunction:: transformers.create_optimizer
-    :members:
 
 Schedules
 ----------------------------------------------------
 
 Learning Rate Schedules
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 .. autofunction:: transformers.get_constant_schedule
 
 
@@ -39,7 +37,6 @@ Learning Rate Schedules
 
 
 .. autofunction:: transformers.get_cosine_schedule_with_warmup
-    :members:
 
 .. image:: /imgs/warmup_cosine_schedule.png
     :target: /imgs/warmup_cosine_schedule.png
@@ -63,7 +60,7 @@ Learning Rate Schedules
 ``Warmup``
 ~~~~~~~~~~~~~~~~
 
-.. autoclass:: transformers.Warmup
+.. autoclass:: transformers.WarmUp
     :members:
 
 Gradient Strategies

docs/source/model_doc/albert.rst

@@ -59,7 +59,7 @@ AlbertForMaskedLM
 
 
 AlbertForSequenceClassification
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.AlbertForSequenceClassification
     :members:

src/transformers/file_utils.py

@@ -121,7 +121,7 @@ def add_start_docstrings_to_callable(*docstr):
         Although the recipe for forward pass needs to be defined within
         this function, one should call the :class:`Module` instance afterwards
         instead of this since the former takes care of running the
-        registered hooks while the latter silently ignores them.
+        pre and post processing steps while the latter silently ignores them.
         """
         fn.__doc__ = intro + note + "".join(docstr) + (fn.__doc__ if fn.__doc__ is not None else "")
         return fn

src/transformers/modeling_albert.py

@@ -423,6 +423,10 @@ ALBERT_INPUTS_DOCSTRING = r"""
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
             :obj:`1` indicates the head is **not masked**, :obj:`0` indicates the head is **masked**.
+        input_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`, defaults to :obj:`None`):
+            Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
+            This is useful if you want more control over how to convert `input_ids` indices into associated vectors
+            than the model's internal embedding lookup matrix.
 """
 
 
@@ -478,6 +482,7 @@ class AlbertModel(AlbertPreTrainedModel):
             inner_group_idx = int(layer - group_idx * self.config.inner_group_num)
             self.encoder.albert_layer_groups[group_idx].albert_layers[inner_group_idx].attention.prune_heads(heads)
 
+    @add_start_docstrings_to_callable(ALBERT_INPUTS_DOCSTRING)
     def forward(
         self,
         input_ids=None,

src/transformers/modeling_tf_utils.py

@@ -91,7 +91,12 @@ class TFPreTrainedModel(tf.keras.Model, TFModelUtilsMixin):
         self.config = config
 
     def get_input_embeddings(self):
-        """ Get model's input embeddings
+        """
+        Returns the model's input embeddings.
+
+        Returns:
+            :obj:`tf.keras.layers.Layer`:
+                A torch module mapping vocabulary to hidden states.
         """
         base_model = getattr(self, self.base_model_prefix, self)
         if base_model is not self:
@@ -100,8 +105,12 @@ class TFPreTrainedModel(tf.keras.Model, TFModelUtilsMixin):
             raise NotImplementedError
 
     def get_output_embeddings(self):
-        """ Get model's output embeddings
-            Return None if the model doesn't have output embeddings
+        """
+        Returns the model's output embeddings.
+
+        Returns:
+            :obj:`tf.keras.layers.Layer`:
+                A torch module mapping hidden states to vocabulary.
         """
         return None  # Overwrite for models with output embeddings