blink/crossencoder/train_cross.py [305:331]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if grad_acc_steps > 1:
                loss = loss / grad_acc_steps

            tr_loss += loss.item()

            if (step + 1) % (params["print_interval"] * grad_acc_steps) == 0:
                logger.info(
                    "Step {} - epoch {} average loss: {}\n".format(
                        step,
                        epoch_idx,
                        tr_loss / (params["print_interval"] * grad_acc_steps),
                    )
                )
                tr_loss = 0

            loss.backward()

            if (step + 1) % grad_acc_steps == 0:
                torch.nn.utils.clip_grad_norm_(
                    model.parameters(), params["max_grad_norm"]
                )
                optimizer.step()
                scheduler.step()
                optimizer.zero_grad()

            if (step + 1) % (params["eval_interval"] * grad_acc_steps) == 0:
                logger.info("Evaluation on the development dataset")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



elq/biencoder/train_biencoder.py [489:515]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if grad_acc_steps > 1:
                loss = loss / grad_acc_steps

            tr_loss += loss.item()

            if (step + 1) % (params["print_interval"] * grad_acc_steps) == 0:
                logger.info(
                    "Step {} - epoch {} average loss: {}\n".format(
                        step,
                        epoch_idx,
                        tr_loss / (params["print_interval"] * grad_acc_steps),
                    )
                )
                tr_loss = 0

            loss.backward()

            if (step + 1) % grad_acc_steps == 0:
                torch.nn.utils.clip_grad_norm_(
                    model.parameters(), params["max_grad_norm"]
                )
                optimizer.step()
                scheduler.step()
                optimizer.zero_grad()

            if (step + 1) % (params["eval_interval"] * grad_acc_steps) == 0:
                logger.info("Evaluation on the development dataset")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -