I am using neuralnet package for training a classifier. The training data looks like this:
> head(train_data)
mvar_12 mvar_40 v10 mvar_1
Try adjusting the threshold to a higher than 0.01 value or the stepmax to more than 1e06, or using a threshold of 0.1 and then decreasing it from there. You can also add in the lifesign = "full" argument to observe the model creation performance in increments of 1000 steps to really dial in the threshold. This "resolved" the non-binary error I had, but the accuracy of the model, the mean squared error, and other results were less than satisfying as a direct result.