Article
Extreme Overtraining in Tiny Language Models
Banaxi-Tech
• • 9
Marcos
mvircs
·
AI & ML interests
None yet
Recent Activity
upvoted an article about 2 hours ago
Extreme Overtraining in Tiny Language Models commentedon an article about 3 hours ago
Extreme Overtraining in Tiny Language Models liked a Space 2 days ago
BananaMind/BananaMindBench-LeaderboardOrganizations
upvoted an article about 2 hours ago
commented on Extreme Overtraining in Tiny Language Models about 3 hours ago
Interesting.
When I test my models, a 40:1 scale always seems to be the most suitable; if it's higher or lower than that, the model's performance suffers.
liked a
Space 2 days ago
liked a
dataset 2 days ago
Nemotron-CC-Math > Fine-Math
1
#2 opened 6 days ago
by mvircs