What does wds mean in learner.fit()

Part 1 (2018)
1

Saw learner.fit(3e-3, 1, wds=1e-6) in lang_model-arxiv and not sure what it meant.

2

I know! :slight_smile: Asked about this earlier :wink: It is just l2 regularization. Additional information where I got it from

1 Like
3

Ohhhh that makes sense! Thanks! Was racking my brains out trying to figure out what that acronym is

1 Like