Is it on purpose? loss for singlelable and multilable switched.

#36
by rhy2023 - opened
        elif self.config.problem_type == "single_label_classification":
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(pooled_logits, labels)
        elif self.config.problem_type == "multi_label_classification":
            loss_fct = BCEWithLogitsLoss()
            loss = loss_fct(pooled_logits, labels)

Sign up or log in to comment