pytorch_transformers/modeling_gpt2.py [708:727]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        hidden_states = transformer_outputs[0]

        lm_logits = self.lm_head(hidden_states)
        mc_logits = self.multiple_choice_head(hidden_states, mc_token_ids).squeeze(-1)

        outputs = (lm_logits, mc_logits) + transformer_outputs[1:]
        if mc_labels is not None:
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(mc_logits.view(-1, mc_logits.size(-1)),
                            mc_labels.view(-1))
            outputs = (loss,) + outputs
        if lm_labels is not None:
            shift_logits = lm_logits[..., :-1, :].contiguous()
            shift_labels = lm_labels[..., 1:].contiguous()
            loss_fct = CrossEntropyLoss(ignore_index=-1)
            loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)),
                            shift_labels.view(-1))
            outputs = (loss,) + outputs

        return outputs  # (lm loss), (mc loss), lm logits, mc logits, presents, (all hidden_states), (attentions)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



pytorch_transformers/modeling_openai.py [701:720]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        hidden_states = transformer_outputs[0]

        lm_logits = self.lm_head(hidden_states)
        mc_logits = self.multiple_choice_head(hidden_states, mc_token_ids).squeeze(-1)

        outputs = (lm_logits, mc_logits) + transformer_outputs[1:]
        if mc_labels is not None:
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(mc_logits.view(-1, mc_logits.size(-1)),
                            mc_labels.view(-1))
            outputs = (loss,) + outputs
        if lm_labels is not None:
            shift_logits = lm_logits[..., :-1, :].contiguous()
            shift_labels = lm_labels[..., 1:].contiguous()
            loss_fct = CrossEntropyLoss(ignore_index=-1)
            loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)),
                            shift_labels.view(-1))
            outputs = (loss,) + outputs

        return outputs  # (lm loss), (mc loss), lm logits, mc logits, (all hidden_states), (attentions)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -