Train-val accuracy logging

[kgarg8]

Hi Sungyub Kim,

Thanks for the great implementation.

I have a question about your code here:

GBML/main.py

Lines 69 to 71 in 1577e17

	train_loss, train_acc, train_grad = train(args, model, train_loader)
	valid_loss, valid_acc = valid(args, model, valid_loader)
	test_loss, test_acc = valid(args, model, test_loader)

Here, you are first training on all the batches in the meta-train set, then you are doing validation and testing.
However, the original algorithm seems to record the testing accuracy after training on every batch of tasks in the meta-train set. Do you observe the difference? I know it is a matter of implementation, we could have done the testing simultaneously, but as a matter of keeping consistent with the original implementation and the way others report their accuracy, would it make sense to observe the testing accuracy immediately after training on 1 meta-batch?

Thanks