Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Model Pre-training on FineWeb-Edu
Loading...
14.13
Perplexity
Muown
11.1692
31.1546
51.14
71.1254
May 11, 2026
Perplexity
Updated 22d ago
Evaluation Results
Method
Method
Links
Perplexity
Muown
η (learning rate)=4 ×...
2026.05
14.13
Muown
η (learning rate)=2 ×...
2026.05
14.14
Muown
η (learning rate)=1 ×...
2026.05
14.24
Muon
η (learning rate)=2 ×...
2026.05
14.37
Muon
η (learning rate)=2 ×...
2026.05
14.4
Muon
η (learning rate)=1 ×...
2026.05
14.44
SOAP
η (learning rate)=2 ×...
2026.05
14.47
SOAP
η (learning rate)=1 ×...
2026.05
14.49
SOAP
η (learning rate)=4 ×...
2026.05
14.53
Muon
η (learning rate)=1 ×...
2026.05
14.54
Muon
η (learning rate)=4 ×...
2026.05
28.37
Muon
η (learning rate)=4 ×...
2026.05
88.15
Feedback
Search any
task
Search any
task