SelanjutnyaPanduan berikutnya
Hukum Penskalaan untuk Jaringan Neural
Dasar-dasar
PANDUAN AI Bahasa
Chinchilla studied how to allocate a training-compute budget between parameters and training tokens.
Dengarkan panduan iniDiceritakan oleh AI · ~2 min
Its fitted results favor scaling both together in the evaluated regime; that objective is different from minimizing total deployment cost or guaranteeing one token ratio for every dataset.
The 2022 study fitted loss behavior across model and data budgets and estimated training-compute-optimal parameter and token allocations. The finding that both quantities should grow in similar proportions means comparable scaling exponents, not equal numerical counts. Chinchilla used about seventy billion parameters and 1.4 trillion training tokens, giving a twenty-token-per-parameter example. It was compared with the much larger Gopher under a comparable training-compute budget. The study argued that many evaluated contemporary large models were undertrained relative to the estimated optimum. These relationships are fitted results that depend on the data and setup; a fixed ratio is not a universal design law. LLaMA's paper discusses training smaller models longer as a way to consider inference efficiency, a different objective from training compute alone.
Comparing the 70-billion-parameter Chinchilla experiment with the 280-billion-parameter Gopher baseline.
Using fitted training-budget relationships as a starting point rather than a universal ratio rule.
Distinguishing a from-scratch training optimum from a smaller model chosen for repeated inference.
Evaluating whether parameters or data provide more value under a defined compute and quality objective.
Scaling research continues to examine data quality, repeated data, model architecture, and the cost of training versus serving. State the objective and evaluation conditions before calling an allocation optimal. A useful empirical trend is different from a guarantee that one parameter-token recipe dominates every workload.
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
Chinchilla studied how to allocate a training-compute budget between parameters and training tokens. Its fitted results favor scaling both together in the evaluated regime; that objective is different from minimizing total deployment cost or guaranteeing one token ratio for every dataset.
Similar proportional growth is not a literal one-token-per-parameter rule.
1.4 trillion divided by seventy billion equals twenty; this example is not a universal optimum for every setup.
Chinchilla dengan parameter 70B mengalahkan Gopher dengan parameter 280B milik DeepMind menggunakan komputasi yang sama, karena ia melatih data yang jauh lebih banyak.
Banyak model besar pada masa itu yang belum dilatih, yang berarti model tersebut akan berperforma lebih baik dengan lebih banyak data untuk jumlah parameternya.
Komputasi pelatihan (FLOP) kira-kira sebanding dengan jumlah parameter dikalikan dengan jumlah token pelatihan.
Teruslah belajar
Panduan lainnya dipilih untuk topik ini
SelanjutnyaPanduan berikutnya
Hukum Penskalaan untuk Jaringan Neural
Dasar-dasar