Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Language Modeling on Fineweb-edu 1.0 (test)
Loading...
2.32
LM Loss
Random Sampling KD (Ours 12+)
2.3128
2.3614
2.41
2.4586
Mar 21, 2025
LM Loss
Updated 4d ago
Evaluation Results
Method
Method
Links
LM Loss
Random Sampling KD (Ours 12+)
Student Size=3B, Teach...
2025.03
2.32
FullKD
Student Size=3B, Teach...
2025.03
2.34
Random Sampling KD (Ours 12)
Student Size=3B, Teach...
2025.03
2.35
CE
Student Size=3B, Teach...
2025.03
2.37
Top-K 50
Student Size=3B, Teach...
2025.03
2.4
Top-K 12
Student Size=3B, Teach...
2025.03
2.5
Feedback
Search any
task
Search any
task