tabensemb.model.WideDeep._train_single_model

method

WideDeep._train_single_model(model, model_name, epoch, X_train, y_train, X_val, y_val, verbose, warm_start, in_bayes_opt, **kwargs)

pytorch_widedeep uses an approximated loss calculation procedure that calculates the average loss across batches, which is not what we do (in a precise way for MSE) at the end of training and makes results from the callback differ from our final metrics.