Posts by Tags

language models

From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes

scaling laws

From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes

stochastic optimization

From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law Regimes