Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
MIT License
Explorations into "Grokfast, Accelerated Grokking by Amplifying Slow Gradients", out of Seoul National University in Korea. In particular, will compare it with NAdam on modular addition as well as a few other tasks, since I am curious why those experiments are left out of the paper. If it holds up, will polish it up into a nice package for quick use.
The official repository can be found here
$ pip install grokfast-pytorch
import torch
from torch import nn
# toy model
model = nn.Linear(10, 1)
# import GrokFastAdamW and instantiate with parameters
from grokfast_pytorch import GrokFastAdamW
opt = GrokFastAdamW(
model.parameters(),
lr = 1e-4,
weight_decay = 1e-2
)
# forward and backwards
loss = model(torch.randn(10))
loss.backward()
# optimizer step
opt.step()
opt.zero_grad()
exp_avg
could be repurposed for amplifying slow grads@inproceedings{Lee2024GrokfastAG,
title = {Grokfast: Accelerated Grokking by Amplifying Slow Gradients},
author = {Jaerin Lee and Bong Gyun Kang and Kihoon Kim and Kyoung Mu Lee},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:270123846}
}
@misc{kumar2024maintaining,
title={Maintaining Plasticity in Continual Learning via Regenerative Regularization},
author={Saurabh Kumar and Henrik Marklund and Benjamin Van Roy},
year={2024},
url={https://openreview.net/forum?id=lyoOWX0e0O}
}