issues
search
lucidrains
/
grokfast-pytorch
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
MIT License
83
stars
4
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
The question about learning rate normalization
#5
pkorobov
opened
3 months ago
0
Different math?
#4
brockbrownwork
opened
3 months ago
2
Thanks for trying our work
#2
ironjr
opened
3 months ago
2
Seems to work for me
#1
inspirit
opened
3 months ago
13