A custom convergence measure applied to a 96k-parameter decoder-only transformer shows learning-rate boundaries between convergent and divergent training are fractal-like across zoom levels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mapping the Edge of Chaos: Fractal-Like Boundaries in The Trainability of Decoder-Only Transformer Models
A custom convergence measure applied to a 96k-parameter decoder-only transformer shows learning-rate boundaries between convergent and divergent training are fractal-like across zoom levels.