Customizable loss reduction breaks assumptions

[bhancock8]

PR #75 introduced a customizable reduction for the loss function, but there are two places later in the code where we make the assumption that its the total loss (reduction='sum') when we go to calculate the average loss per example:

1. metal/metal/classifier.py

   Line 222 in 31587d4

   running_loss = epoch_loss / (len(data[0]) * (batch_num + 1))

2. metal/metal/classifier.py

   Line 228 in 31587d4

   train_loss = epoch_loss / len(train_loader.dataset)

I think we either need to set it to sum and allow post-processing if they want to combine in some other way, or add some special handling so that we're not dividing by train set size twice. I think I'd probably be in favor of always calculating some and then dividing later. What was the motivation for allowing it to be changed?

[ajratner]

Good call, will fix!

[brahmaneya]

Active development is being moved to our main repo, https://github.com/snorkel-team/snorkel. The model there does not have this issue.