Ctrl for sequence classification (#8812)

* add CTRLForSequenceClassification

* pass local test

* merge with master

* fix modeling test for sequence classification

* fix deco

* fix assert

src/transformers/models/ctrl/__init__.py

@@ -8,7 +8,13 @@ from .tokenization_ctrl import CTRLTokenizer
 
 
 if is_torch_available():
-    from .modeling_ctrl import CTRL_PRETRAINED_MODEL_ARCHIVE_LIST, CTRLLMHeadModel, CTRLModel, CTRLPreTrainedModel
+    from .modeling_ctrl import (
+        CTRL_PRETRAINED_MODEL_ARCHIVE_LIST,
+        CTRLForSequenceClassification,
+        CTRLLMHeadModel,
+        CTRLModel,
+        CTRLPreTrainedModel,
+    )
 
 if is_tf_available():
     from .modeling_tf_ctrl import (

src/transformers/models/ctrl/modeling_ctrl.py

@@ -18,10 +18,10 @@
 import numpy as np
 import torch
 import torch.nn as nn
-from torch.nn import CrossEntropyLoss
+from torch.nn import CrossEntropyLoss, MSELoss
 
 from ...file_utils import add_code_sample_docstrings, add_start_docstrings, add_start_docstrings_to_model_forward
-from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
+from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutput
 from ...modeling_utils import Conv1D, PreTrainedModel, find_pruneable_heads_and_indices, prune_linear_layer
 from ...utils import logging
 from .configuration_ctrl import CTRLConfig
@@ -571,3 +571,117 @@ class CTRLLMHeadModel(CTRLPreTrainedModel):
             hidden_states=transformer_outputs.hidden_states,
             attentions=transformer_outputs.attentions,
         )
+
+
+@add_start_docstrings(
+    """
+    The CTRL Model transformer with a sequence classification head on top (linear layer).
+    :class:`~transformers.CTRLForSequenceClassification` uses the last token in order to do the classification, as
+    other causal models (e.g. GPT-2) do. Since it does classification on the last token, it requires to know the
+    position of the last token. If a :obj:`pad_token_id` is defined in the configuration, it finds the last token that
+    is not a padding token in each row. If no :obj:`pad_token_id` is defined, it simply takes the last value in each
+    row of the batch. Since it cannot guess the padding tokens when :obj:`inputs_embeds` are passed instead of
+    :obj:`input_ids`, it does the same (take the last value in each row of the batch).
+    """,
+    CTRL_START_DOCSTRING,
+)
+class CTRLForSequenceClassification(CTRLPreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.num_labels = config.num_labels
+        self.transformer = CTRLModel(config)
+        self.classifier = nn.Linear(config.n_embd, self.num_labels, bias=False)
+
+        self.init_weights()
+
+    @add_start_docstrings_to_model_forward(CTRL_INPUTS_DOCSTRING)
+    @add_code_sample_docstrings(
+        tokenizer_class=_TOKENIZER_FOR_DOC,
+        checkpoint="ctrl",
+        output_type=SequenceClassifierOutput,
+        config_class=_CONFIG_FOR_DOC,
+    )
+    def forward(
+        self,
+        input_ids=None,
+        past_key_values=None,
+        attention_mask=None,
+        token_type_ids=None,
+        position_ids=None,
+        head_mask=None,
+        inputs_embeds=None,
+        labels=None,
+        use_cache=None,
+        output_attentions=None,
+        output_hidden_states=None,
+        return_dict=None,
+    ):
+        r"""
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
+            Labels for computing the sequence classification/regression loss. Indices should be in :obj:`[0, ...,
+            config.num_labels - 1]`. If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
+            If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
+        """
+
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        transformer_outputs = self.transformer(
+            input_ids,
+            past_key_values=past_key_values,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+
+        hidden_states = transformer_outputs[0]
+        logits = self.classifier(hidden_states)
+
+        if input_ids is not None:
+            batch_size, sequence_length = input_ids.shape[:2]
+        else:
+            batch_size, sequence_length = inputs_embeds.shape[:2]
+
+        assert (
+            self.config.pad_token_id is not None or batch_size == 1
+        ), "Cannot handle batch sizes > 1 if no padding token is defined."
+
+        if self.config.pad_token_id is None:
+            sequence_lengths = -1
+        else:
+            if input_ids is not None:
+                sequence_lengths = torch.ne(input_ids, self.config.pad_token_id).sum(-1) - 1
+            else:
+                sequence_lengths = -1
+                logger.warning(
+                    f"{self.__class__.__name__} will not detect padding tokens in `inputs_embeds`. Results may be "
+                    f"unexpected if using padding tokens in conjuction with `inputs_embeds.`"
+                )
+
+        pooled_logits = logits[range(batch_size), sequence_lengths]
+
+        loss = None
+        if labels is not None:
+            if self.num_labels == 1:
+                #  We are doing regression
+                loss_fct = MSELoss()
+                loss = loss_fct(pooled_logits.view(-1), labels.to(self.dtype).view(-1))
+            else:
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(pooled_logits.view(-1, self.num_labels), labels.view(-1))
+
+        if not return_dict:
+            output = (pooled_logits,) + transformer_outputs[2:]
+            return ((loss,) + output) if loss is not None else output
+
+        return SequenceClassifierOutput(
+            loss=loss,
+            logits=pooled_logits,
+            hidden_states=transformer_outputs.hidden_states,
+            attentions=transformer_outputs.attentions,
+        )