Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Sheria za Kuongeza Kiwango cha Chinchilla

Jaribu matokeo ya bajeti ya mafunzo ya Chinchilla, mfano wa 70B/1.4T, uwiano wa kuongeza, makadirio ya kukokotoa, na tofauti na uboreshaji wa utumaji.

Njia za mwongozo zinazohusianaSheria za Kupunguza Chinchilla
Swali 1 ya 8

What does Chinchilla's finding that parameters and tokens should scale in similar proportions mean?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. What does Chinchilla's finding that parameters and tokens should scale in similar proportions mean?
    • Both should grow with comparable scaling exponents under the studied training-compute objective
    • The numerical token count must equal the parameter count
    • Training data does not affect the fitted loss
    • Every deployment must choose the largest possible model
  2. What token-per-parameter ratio does the 70B-parameter, 1.4T-token Chinchilla experiment illustrate?
    • Exactly one token per parameter
    • About two thousand tokens per parameter
    • About twenty training tokens per parameter
    • A ratio determined only by the number of GPUs
  3. Je, Chinchilla alishinda mtindo gani licha ya kuwa mdogo zaidi?
    • GPT-2
    • Gopher
    • BERT
    • Mamba
  4. Chinchilla ilimaanisha nini kuhusu mifano kama GPT-3 wakati huo?
    • Walizoezwa kupita kiasi
    • Walikuwa na kompyuta ndogo sana
    • Walitumia ishara isiyo sahihi
    • Walikuwa wamefunzwa kidogo ikilinganishwa na saizi yao
  5. Takriban ni jinsi gani hesabu ilikadiriwa katika uchanganuzi wa Chinchilla?
    • Sawa na idadi ya GPU pekee
    • Hutegemea saizi ya data
    • Sawa na vigezo nyakati za mafunzo tokeni
    • Sawa na saizi ya msamiati
  6. Why might a deployment objective favor a smaller model trained on extra data rather than the training-compute optimum alone?
    • Repeated inference costs can matter alongside the initial training budget
    • Inference has no resource cost for any model
    • The Chinchilla study proved every scaling relationship false
    • More data always reduces both training and serving work to zero
  7. Under the approximation that training compute is proportional to N times D, how must D change if N doubles while that compute budget stays fixed?
    • D must also double
    • D must quadruple
    • D must remain unchanged
    • D must approximately halve
  8. Which three types of term appear in Chinchilla’s parametric loss fit?
    • Only GPU count, electricity price, and elapsed seconds
    • An irreducible base term, a model-size contribution, and a data-size contribution
    • Only vocabulary size, file size, and model name
    • Only a linear token count with no model-size term