Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Horizon Generalization on FOL Sine-trend reward
Loading...
186.81
Max LR Value
Gemma-2-9b-it
49.0308
84.8004
120.57
156.3396
Nov 6, 2025
Max LR Value
Avg LR Value
Beta
Updated 2d ago
Evaluation Results
Method
Method
Links
Max LR Value
Avg LR Value
Beta
Gemma-2-9b-it
Horizon Shift=T=25 to...
2025.11
186.81
18
48
Trained Gemma-2-9b-it
Horizon Shift=T=25 to...
2025.11
139.79
13.28
38
FTRL
Horizon Shift=T=25 to...
2025.11
54.33
12.32
31
Feedback
Search any
task
Search any
task