A one-parameter coupling of model size and data in the Chinchilla loss form reduces boundary prediction error and enables cheaper L-shaped profiling grids.
For instance, a broadly mistuned grid might artificially dampen the measured interaction or skew the optimal ratio
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Skaling: Chinchilla's Exponents Meet Kaplan's Coupling
A one-parameter coupling of model size and data in the Chinchilla loss form reduces boundary prediction error and enables cheaper L-shaped profiling grids.