Scaling Law Fitting on LLM-wikipedia (test)
0.0854MREPBH
Evaluation Results
| Method | Links | |
|---|---|---|
| PBHN=5, Dimension (d)=19, LBFGS steps=5, CPU time=300s, Gamma=10, Delta=10^-3, Seeds=32026.05 | 0.0854 | |
| PBHN=15, Dimension (d)=19, LBFGS steps=5, CPU time=300s, Gamma=10, Delta=10^-3, Seeds=32026.05 | 0.0855 | |
| PBHN=10, Dimension (d)=19, LBFGS steps=5, CPU time=300s, Gamma=10, Delta=10^-3, Seeds=32026.05 | 0.0948 | |
| ZOPN=5, Dimension (d)=19, LBFGS steps=5, CPU time=300s, Gamma=10, Delta=10^-3, Seeds=32026.05 | 0.1042 | |
| BHDimension (d)=19, LBFGS steps=5, CPU time=300s, Gamma=10, Delta=10^-3, Seeds=32026.05 | 0.139 | |
| PBHN=5, d=47, lbfgs steps=52026.05 | 19.285 | |
| PBHN=20, d=47, lbfgs steps=52026.05 | 19.398 | |
| PBHN=10, d=47, lbfgs steps=52026.05 | 19.407 | |
| PBHN=5, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.658 | |
| PBHN=20, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.664 | |
| PBHN=40, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.739 | |
| BHd=47, lbfgs steps=52026.05 | 19.744 | |
| PBHN=50, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.749 | |
| BHlbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.827 | |
| PBHN=10, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.859 | |
| PBHN=15, d=47, lbfgs steps=52026.05 | 19.909 | |
| PBHN=30, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 19.915 | |
| PBHN=50, d=47, lbfgs steps=52026.05 | 19.93 | |
| PBHN=30, d=47, lbfgs steps=52026.05 | 19.976 | |
| PBHN=15, lbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 20.044 | |
| PBHN=40, d=47, lbfgs steps=52026.05 | 20.077 | |
| ZOPd=47, lbfgs steps=52026.05 | 20.529 | |
| ZOPlbfgs steps=10, CPU time=300s, d=47, seeds=32026.05 | 20.529 |