SıradakiSonraki rehber
Evrişimsel Sinir Ağları
Temeller
Temel Bilgiler KILAVUZU
Scaling laws are empirical relationships between language-model loss and quantities such as parameters, training data, and compute.
Bu kılavuzu dinleyinAI tarafından anlatılan · ~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.
Ücretsiz bülten
Hafta içi her sabah sade İngilizce yazılmış, doğrulanmış üç yapay zeka hikayesi. Sonsuza kadar ücretsiz, reklam yok.
Hafta içi her gün bir e-posta. Tek tıklamayla aboneliğinizi iptal edin. Adresinizi asla satmayız veya paylaşmayız.
Kendinizi test edin
Her yanıtla ilgili anında geri bildirim ve bir kursu geçtiğinizde doğrulanabilir bir kimliğe sahip paylaşılabilir bir sertifika.
Ücretsiz AI eğitimini destekleyin. AI Understanding, bir 501(c)(3) kâr amacı gütmeyen kuruluştur; hiçbir zaman reklam yoktur, ödeme duvarı yoktur. Bağış yap
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 ve ark. parametre sayısında (N), eğitim belirteçlerinde (D) ve toplam hesaplamada (C) güç yasası olarak kaybı inceledi.
Fitted curves can inform large-run forecasts from smaller experiments, but changes in data, architecture, or training conditions can limit extrapolation.
Kayıp, ölçekle küçülen azaltılabilir bir kısma ve verinin doğasında bulunan rastgelelik tarafından belirlenen indirgenemez bir tabana sahiptir.
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.
Öğrenmeye devam et
Bu konu için daha fazla rehber seçildi
SıradakiSonraki rehber
Evrişimsel Sinir Ağları
Temeller