You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I notice that Adam gets the same test set avg loss after epoch 1 as SGD gets after epoch 5, but Adam never improves during epochs 2-5. I guess my loss is so small (0.04) that there's nothing more to learn?
L119: Change to AdamW or Adam (less need to tune LR)
L85: no relus after final layer
L95: check docs to see if you are applying softmax twice by accident from nn.CrossEntropy
csknow/learn_bot/learn_bot/bot.py
Line 118 in f1551f4
The text was updated successfully, but these errors were encountered: