Keller Jordan
@kellerjordan0
CIFAR-10 fanatic
Pretraining @OpenAI OpCo LLC.
가입 March 2016
428 팔로잉 중 16.9K 팬
New modded-NanoGPT optimization benchmark result: @wen_kaiyue has improved upon both the Muon and AdamW baselines, by replacing their weight decay with hyperball optimization. The new record is 3325 steps.
더 보기
