biolm/run_classification.py [188:203]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                    )  # XLM, DistilBERT, RoBERTa, and XLM-RoBERTa don't use segment_ids
                outputs = model(**inputs)
                loss = outputs[0]  # model outputs are always tuple in transformers (see doc)

            if args.n_gpu > 1:
                loss = loss.mean()  # mean() to average on multi-gpu parallel training
            if args.gradient_accumulation_steps > 1:
                loss = loss / args.gradient_accumulation_steps

            if args.fp16:
                with amp.scale_loss(loss, optimizer) as scaled_loss:
                    scaled_loss.backward()
            else:
                loss.backward()

            tr_loss += loss.item()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



biolm/run_sequence_labelling.py [177:193]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                )  # XLM and RoBERTa don"t use segment_ids

            outputs = model(**inputs)
            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)

            if args.n_gpu > 1:
                loss = loss.mean()  # mean() to average on multi-gpu parallel training
            if args.gradient_accumulation_steps > 1:
                loss = loss / args.gradient_accumulation_steps

            if args.fp16:
                with amp.scale_loss(loss, optimizer) as scaled_loss:
                    scaled_loss.backward()
            else:
                loss.backward()

            tr_loss += loss.item()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -