Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
🔄
In a Training Loop
41.0
TFLOPS
Joseph Jones
PRO
KlondikeDev
39
9
49
Follow
usamasharif143's profile picture
webxos's profile picture
jobicy's profile picture
47 followers
·
41 following
https://jdj.kunix.org/
klondikedev
KlondikeDev
AI & ML interests
Restoring the Digital Millennium. https://kunix.org/digital-millennium.html
Recent Activity
liked
a model
5 days ago
burner22/numbat
reacted
to
Saccadic-AI
's
post
with 🔥
6 days ago
One neural network. Five mathematical operations. Different learning times. We trained a small mixture-of-experts transformer on addition, subtraction, multiplication, division, and exponentiation modulo 113. The operations didn’t generalize together. Multiplication and division reached 90% held-out accuracy first, followed by exponentiation, subtraction, and finally addition. Multiplication before addition—the reverse of what we expect from a schoolchild. The accuracy chart in the linked article shows why a single overall accuracy number can hide an interesting learning story. Measured with IRIS from Saccadic LLC. More figures and analysis: https://huggingface.co/blog/Saccadic-AI/accuracy-plateaued-the-model-kept-changing Have you observed a similar ordering in multi-task grokking experiments?
upvoted
an
article
6 days ago
Accuracy plateaued. The model kept changing.
View all activity
Organizations
KlondikeDev
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
published
an
article
about 2 months ago
view article
Article
Boris-2-0907 and Boris-2-0917
KlondikeDev
•
Sep 21