A continuaciónSiguiente guía
Redes neuronales convolucionales
Fundamentos
GUÍA DE FUNDAMENTOS
Scaling laws are empirical relationships between language-model loss and quantities such as parameters, training data, and compute.
Escuche esta guíaNarrado por IA · ~2 min
They can help researchers plan experiments and extrapolate within studied regimes, but they do not guarantee an exact result for a new architecture, dataset, or training setup.
Kaplan and colleagues’ 2020 study found empirical power-law relationships between language-model cross-entropy loss and model size, dataset size, and training compute over the regimes they tested. On log-log plots, a power law appears approximately linear. These fitted relationships can be used to estimate outcomes for larger runs, but extrapolations are conditional on comparable training and data setups. The original paper found large models to be more sample-efficient in its experiments and suggested compute-optimal training with relatively large models and fewer tokens than later Chinchilla work recommended. Later studies, including Llama 3, explored training beyond that earlier compute-optimal allocation.
Fitting a loss curve from smaller controlled runs to inform a larger training-budget decision
Comparing parameter and data allocations under a fixed pretraining-compute budget
Checking whether a forecast remains accurate when the data mixture or architecture changes
Separating measured loss trends from downstream capability claims in a model report
Scaling-law research studies new data mixtures, modalities, architectures, and inference-time computation. As training and data regimes change, researchers must remeasure the relevant curves. Scaling laws support resource planning, while downstream accuracy, safety, and reliability require separate evaluation.
Boletín gratuito
Tres noticias verificadas sobre IA cada mañana de lunes a viernes, explicadas con claridad. Gratis para siempre y sin anuncios.
Un correo cada día laborable. Date de baja con un clic. Nunca vendemos ni compartimos tu dirección.
Ponte a prueba
Corrección inmediata en cada respuesta y un certificado para compartir, con un ID verificable, cuando apruebas un curso.
Apoya la educación gratuita sobre IA. AI Understanding es una organización sin fines de lucro 501(c)(3): sin anuncios ni muros de pago, nunca. Hacer una donación
Scaling laws are empirical relationships between language-model loss and quantities such as parameters, training data, and compute. They can help researchers plan experiments and extrapolate within studied regimes, but they do not guarantee an exact result for a new architecture, dataset, or training setup.
Kaplan et al. report empirical power-law relationships over their tested ranges; the fit should not be read as a guarantee outside comparable settings.
Kaplan y cols. estudió la pérdida como una ley de potencia en el recuento de parámetros (N), tokens de entrenamiento (D) y cálculo total (C).
Fitted curves can inform large-run forecasts from smaller experiments, but changes in data, architecture, or training conditions can limit extrapolation.
La pérdida tiene una parte reducible que se reduce con la escala más un piso irreducible establecido por la aleatoriedad inherente de los datos.
With L(X)=E+A·X^-α, a fixed multiplicative increase gives a similar fractional change in the reducible term, but smaller absolute changes as that term shrinks.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Redes neuronales convolucionales
Fundamentos