You are reading immutable version 2. The current guide may be newer.

Study the paper

Scaling Laws for Neural Language Models

Lessons, visuals, quizzes, flashcards, and resources—organized in teaching order.

All activities

Optimal Allocation of Compute Budgets

Intersection point of scaling laws

Intersection point of scaling laws

The intersection point where the scaling laws suggest a potential contradiction or transition is characterized by a compute budget C104C^* \sim 10^4 PF-Days, model size N1012N^* \sim 10^{12} parameters, dataset size D1012D^* \sim 10^{12} tokens, and loss L1.7L^* \sim 1.7 nats/token.

Sources

S6.E8

C∗∼104​PF​-​DaysN∗∼1012​parameters,D∗∼1012​tokens,L∗∼1.7​nats/tokenformulae-sequencesimilar-tosuperscript𝐶superscript104PF-Daysformulae-sequencesimilar-tosuperscript𝑁superscript1012parametersformulae-sequencesimilar-tosuperscript𝐷superscript1012tokenssimilar-tosuperscript𝐿1.7nats/tokenC^{*}\sim 10^{4}\leavevmode\nobreak\ \mathrm{PF}{\text{-}}\mathrm{Days}\quad N^{*}\sim 10^{12}\leavevmode\nobreak\ \text{parameters},\quad D^{*}\sim 10^{12}\leavevmode\nobreak\ \text{tokens},\quad L^{*}\sim 1.7\leavevmode\nobreak\ \text{nats/token} (6.8)
C^{*}\sim 10^{4}\leavevmode\nobreak\ \mathrm{PF}{\text{-}}\mathrm{Days}\quad N^{*}\sim 10^{12}\leavevmode\nobreak\ \text{parameters},\quad D^{*}\sim 10^{12}\leavevmode\nobreak\ \text{tokens},\quad L^{*}\sim 1.7\leavevmode\nobreak\ \text{nats/token}
Reported values
MeasureValue
Sources

S6.E8

C∗∼104​PF​-​DaysN∗∼1012​parameters,D∗∼1012​tokens,L∗∼1.7​nats/tokenformulae-sequencesimilar-tosuperscript𝐶superscript104PF-Daysformulae-sequencesimilar-tosuperscript𝑁superscript1012parametersformulae-sequencesimilar-tosuperscript𝐷superscript1012tokenssimilar-tosuperscript𝐿1.7nats/tokenC^{*}\sim 10^{4}\leavevmode\nobreak\ \mathrm{PF}{\text{-}}\mathrm{Days}\quad N^{*}\sim 10^{12}\leavevmode\nobreak\ \text{parameters},\quad D^{*}\sim 10^{12}\leavevmode\nobreak\ \text{tokens},\quad L^{*}\sim 1.7\leavevmode\nobreak\ \text{nats/token} (6.8)
C^{*}\sim 10^{4}\leavevmode\nobreak\ \mathrm{PF}{\text{-}}\mathrm{Days}\quad N^{*}\sim 10^{12}\leavevmode\nobreak\ \text{parameters},\quad D^{*}\sim 10^{12}\leavevmode\nobreak\ \text{tokens},\quad L^{*}\sim 1.7\leavevmode\nobreak\ \text{nats/token}