Update mlm.py

mlm.py

@@ -525,7 +525,7 @@ class BertEnergyModelForSequenceClassification(BertPreTrainedModel):
     def set_output_embeddings(self, new_embeddings):
         self.lm_head.decoder = new_embeddings
 
-    def forward(self, input_ids, attention_mask=None, labels=None, **kwargs):
+    def forward_mlm(self, input_ids, attention_mask=None, labels=None, **kwargs):
         outputs = self.model(input_ids, attention_mask=attention_mask, **kwargs)
         logits = self.lm_head(outputs.last_hidden_state)
 
@@ -542,4 +542,48 @@ class BertEnergyModelForSequenceClassification(BertPreTrainedModel):
             logits=logits,
             hidden_states=outputs.hidden_states,
             attentions=outputs.attentions,
+        )
+        
+    def forward(self, input_ids, labels=None, return_dict=None, **kwargs):
+        if return_dict is None:
+            return_dict = self.return_dict
+
+        outputs = self.model(input_ids, attention_mask=attention_mask, **kwargs)
+        last_hidden_state = self.norm(outputs.last_hidden_state)
+
+        x = last_hidden_state[:, 0, :]
+        x = self.dropout(x)
+        logits = self.classifier(x)
+
+        loss = None
+        if labels is not None:
+            labels = labels.to(logits.device)
+
+            if self.config.problem_type is None:
+                if self.num_labels == 1:
+                    self.config.problem_type = "regression"
+                elif self.num_labels > 1 and labels.dtype in (torch.long, torch.int):
+                    self.config.problem_type = "single_label_classification"
+                else:
+                    self.config.problem_type = "multi_label_classification"
+
+            if self.config.problem_type == "regression":
+                loss_fct = MSELoss()
+                loss = loss_fct(logits.squeeze(), labels.squeeze()) if self.num_labels == 1 else loss_fct(logits, labels)
+            elif self.config.problem_type == "single_label_classification":
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+            else:
+                loss_fct = BCEWithLogitsLoss()
+                loss = loss_fct(logits, labels)
+
+        if not return_dict:
+            output = (logits, outputs.hidden_states, outputs.attentions)
+            return ((loss,) + output) if loss is not None else output
+
+        return SequenceClassifierOutput(
+            loss=loss,
+            logits=logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
         )