SelanjutnyaPanduan berikutnya
Jaringan Neural Konvolusional
Dasar-dasar
PANDUAN Dasar
Scaling laws are empirical relationships between language-model loss and quantities such as parameters, training data, and compute.
Dengarkan panduan iniDiceritakan oleh AI · ~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.
Buletin gratis
Tiga cerita AI terverifikasi setiap pagi hari kerja, ditulis dalam bahasa Inggris sederhana. Gratis selamanya, tanpa iklan.
Satu email setiap hari kerja. Berhenti berlangganan dalam satu klik. Kami tidak pernah menjual atau membagikan alamat Anda.
Uji diri Anda sendiri
Umpan balik instan untuk setiap jawaban, dan sertifikat yang dapat dibagikan dengan ID yang dapat diverifikasi setelah Anda lulus kursus.
Mendukung pendidikan AI gratis. AI Understanding adalah organisasi nirlaba 501(c)(3) — tanpa iklan, tanpa paywall, selamanya. Berikan sumbangan
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 dkk. mempelajari kerugian sebagai hukum pangkat dalam jumlah parameter (N), token pelatihan (D), dan total komputasi (C).
Fitted curves can inform large-run forecasts from smaller experiments, but changes in data, architecture, or training conditions can limit extrapolation.
Kerugian memiliki bagian yang dapat direduksi yang menyusut seiring dengan skala ditambah batas bawah yang tidak dapat direduksi yang ditentukan oleh keacakan bawaan data.
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.
Teruslah belajar
Panduan lainnya dipilih untuk topik ini
SelanjutnyaPanduan berikutnya
Jaringan Neural Konvolusional
Dasar-dasar