v1 is a bit over trained due to a couple of negative TIs I used during testing. Embarrassing! Since I'd already scrubbed most of the data, v2 represents fresh training. It looks great and makes me feel better about having it out there.
v1 is a bit over trained due to a couple of negative TIs I used during testing. Embarrassing! Since I'd already scrubbed most of the data, v2 represents fresh training. It looks great and makes me feel better about having it out there.