fixed init_weight

pytorch_transformers/modeling_roberta.py

@@ -418,7 +418,7 @@ class RobertaForMultipleChoice(BertPreTrainedModel):
         self.dropout = nn.Dropout(config.hidden_dropout_prob)
         self.classifier = nn.Linear(config.hidden_size, 1)
 
-        self.apply(self.init_weights)
+        self.init_weights()
 
     def forward(self, input_ids, token_type_ids=None, attention_mask=None, labels=None,
                 position_ids=None, head_mask=None):