Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Modular Addition on Modular Addition f_train=0.5 P=97
Loading...
2,460
Grokking Onset (epochs)
Norm Penalty
1,936.8
5,468.4
9,000
12,531.6
Jun 30, 2026
Grokking Onset (epochs)
Speedup Factor
Updated 25d ago
Evaluation Results
Method
Method
Links
Grokking Onset (epochs)
Speedup Factor
Norm Penalty
Architecture=MLP, Regu...
2026.06
2,460
6.3
Norm Penalty
Architecture=Transform...
2026.06
5,200
1.5
Strong WD Baseline
Architecture=Transform...
2026.06
8,000
-
Strong WD Baseline
Architecture=MLP, Regu...
2026.06
15,540
-
Feedback
Search any
task
Search any
task