Up tókànItọsọna atẹle
Awọn Ofin Iwọn fun Awọn Nẹtiwọọki Neural
Awọn ipilẹ
Èdè AI Itọsọna
Awọn ofin iwọntunwọnsi Chinchilla
Chinchilla studied how to allocate a training-compute budget between parameters and training tokens.
Gbọ si itọsọna yiiAI-ṣe afihan · ~2 min
Lori iwe yi2 min ka
Akopọ
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.
Jin Dive
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.
Real-World imuse
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.
Ọjọ iwaju ti Awọn ofin Iwọn iwọn Chinchilla
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.
Fifi o sinu iwa
Kini idi ti o ṣe pataki
- Iyara ati iwọn. Ṣiṣan iṣẹ ede le gbe ni iyara laisi irubọ aitasera.
- Wiwọle ati arọwọto. O faagun iraye si kọja awọn ede ati awọn aza ibaraẹnisọrọ.
- Awọn ipinnu diẹ sii. Awọn ẹgbẹ le lo akoko diẹ sii lori idajọ lakoko ti adaṣe n kapa atunwi.
Ṣọra fun
- Awọn otitọ ti a sọ di mimọ le tẹ awọn ijabọ sii ni idakẹjẹ, awọn ṣiṣan atilẹyin, tabi awọn abajade iwadii.
- Ifamọ kiakia le ṣẹda awọn abajade aisedede kọja awọn ibeere ti o jọra.
- Awọn data ọrọ ifarabalẹ le farahan ti awọn idari wiwọle ko lagbara.
Next awọn igbesẹ
- Ṣetumo ọna kika iṣẹjade, ohun orin, ati awọn iṣedede didara ṣaaju ṣiṣejade.
- Awọn idahun ilẹ pẹlu awọn orisun ti o gbẹkẹle nigbakugba ti deede ba ṣe pataki.
- Jeki aaye ayẹwo atunyẹwo eniyan fun awọn abajade ti o ga julọ.
- Tọpinpin awọn ilana ikuna ati tunṣe awọn itọsi tabi ṣiṣan iṣẹ nigbagbogbo.
Tesiwaju Ṣiṣawari
Ìwé ìròyìn ọfẹ
Gba ìkànìyàn AI ojoojúmọ́
Ìtàn AI mẹta tó jẹ́rìí ní gbogbo owurọ́ ọjọ́ iṣẹ́, kọ́wé ní Gẹ̀ẹ́sì tó rọrùn. Ọfẹ́ fún gbogbo àkókò, kò sí ìpolówó.
Ìmeèlì kan ní gbogbo ọjọ́ iṣẹ́. Yọkúrò ní ìkànìyàn ní ìkànìyàn kan. A kò ta tàbí pín àdírẹ́sì rẹ.
Ṣe idanwo fun ara rẹ
Take the Chinchilla Scaling Laws quiz
Ìdáhùn lẹ́sẹ̀kẹsẹ̀ lórí gbogbo ìdáhùn, àti iwe-ẹ̀rí tó lè pin pẹ̀lú ID tó lè jẹ́rìí lẹ́yìn tí o bá kọ́ ẹ̀kọ́.
Ṣe àtìlẹ́yìn ẹ̀kọ́ AI ọfẹ́. AI Understanding jẹ́ àjọ àìní èrè 501(c)(3) — kò sí ìpolówó, kò sí àkúnya owó, ní gbogbo àkókò. Ṣe ẹbun kan
Awọn ibeere ti a beere nigbagbogbo
What is Chinchilla Scaling Laws?
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.
What does Chinchilla's finding that parameters and tokens should scale in similar proportions mean?
Similar proportional growth is not a literal one-token-per-parameter rule.
What token-per-parameter ratio does the 70B-parameter, 1.4T-token Chinchilla experiment illustrate?
1.4 trillion divided by seventy billion equals twenty; this example is not a universal optimum for every setup.
Awoṣe wo ni Chinchilla ṣe ju bi o ti jẹ pe o kere pupọ?
70B-paramita Chinchilla lu DeepMind ti ara 280B-paramita Gopher lilo kanna oniṣiro, nitori ti o oṣiṣẹ lori jina siwaju sii data.
Kini Chinchilla tumọ si nipa awọn awoṣe bii GPT-3 ni akoko yẹn?
Ọpọlọpọ awọn awoṣe nla ti akoko yẹn ko ni ikẹkọ, afipamo pe wọn yoo ti ṣe dara julọ pẹlu data pupọ diẹ sii fun kika paramita wọn.
Ni aijọju bawo ni iṣiro ṣe isunmọ ni itupalẹ Chinchilla?
Iṣiro ikẹkọ (FLOPs) jẹ isunmọ iwọn si nọmba awọn aye ti a pọ nipasẹ nọmba awọn ami ikẹkọ.
Tesiwaju kikọ
Jẹmọ awọn itọsọna
Awọn itọsọna diẹ sii ti a yan fun koko yii