Als nächstesNächster Leitfaden
Testzeittraining
Grundlagen
Grundlagen-Leitfaden
The Chinchilla paper estimates training-compute allocations with three complementary methods: training-curve envelopes, IsoFLOP profiles, and a parametric loss fit.
Hören Sie sich diesen Leitfaden anKI-erzählt · ~2 min
It matters because its measured range and estimation methods show how researchers can cross-check a compute-optimal forecast rather than rely on one extrapolation.
Hoffmann and colleagues trained over 400 language models, from about 70 million to over 16 billion parameters, on roughly 5 billion to 500 billion tokens. They used three approaches to estimate how model size and training tokens should share a compute budget. First, they fixed model sizes, varied training horizons, smoothed and interpolated training curves, and selected the lowest loss for a given FLOP count. Second, they constructed IsoFLOP profiles by varying model size at fixed compute budgets and fitting the loss minimum on each profile. Third, they fit a parametric loss function over parameter count and token count, using Huber loss and L-BFGS with a grid of initializations. The three methods produced similar near-equal scaling estimates in the studied regime. Chinchilla itself was a 70B model trained on 1.4T tokens using MassiveText, with a slightly different subset distribution from Gopher.
Hold several model sizes fixed and vary training duration to estimate minimum loss at different compute budgets
Build IsoFLOP profiles by comparing model sizes at fixed compute budgets and locating each loss minimum
Fit a parametric loss function of model size and training tokens, then compare its frontier with curve-based estimates
Check a forecast against the data and training recipe used for the 70B Chinchilla model
Scaling studies can become more informative when they compare several estimation methods, vary dataset mixtures, and test their predictions on separately trained models. Forecasts beyond the measured parameter and token ranges remain uncertain. Future work should report the sweep design, fit assumptions, and evaluation data alongside any compute-optimal recommendation.
Kostenloser Newsletter
Drei verifizierte KI-Geschichten jeden Werktagmorgen, in einfachem Englisch geschrieben. Für immer kostenlos, keine Werbung.
Eine E‑Mail jeden Werktag. Abmelden mit einem Klick. Wir verkaufen oder teilen Ihre Adresse nie.
Testen Sie sich selbst
Sofortiges Feedback zu jeder Antwort und ein teilbares Zertifikat mit verifizierbarer ID, sobald Sie einen Kurs bestanden haben.
Unterstützen Sie kostenlose KI-Bildung. AI Understanding ist eine 501(c)(3) gemeinnützige Organisation – keine Werbung, keine Paywall, nie. Machen Sie eine Spende
The Chinchilla paper estimates training-compute allocations with three complementary methods: training-curve envelopes, IsoFLOP profiles, and a parametric loss fit. It matters because its measured range and estimation methods show how researchers can cross-check a compute-optimal forecast rather than rely on one extrapolation.
The paper reports training over 400 models as part of its parameter and token sweep.
The paper describes a sweep ranging from about 70M to over 16B parameters.
The study reports training runs on roughly 5B to 500B tokens.
Approach 1 fixes model sizes and trains each across different horizons, then uses smoothed training curves to estimate minimum loss per FLOP.
Approach 2 compares final loss across model sizes at fixed FLOP budgets and locates the loss minimum.
Lerne weiter
Weitere Leitfäden zu diesem Thema ausgewählt
Als nächstesNächster Leitfaden
Testzeittraining
Grundlagen