Ubuyobozi bwa tekiniki

Adam na Adaptive Optimizers

Adam ni akazi keza cyane inyuma yimiyoboro myinshi igezweho, ihita ihuza igipimo cyo kwiga kuri buri kintu cyose.

Incamake

Adam ni akazi keza cyane inyuma yimiyoboro myinshi igezweho, ihita ihuza igipimo cyo kwiga kuri buri kintu cyose. Nibyingenzi kuko ituma imyitozo yimbitse yihuta kandi ntigabanuke cyane kuruta kumanuka gahoro gahoro.

Adam na Adaptive Optimizers nigikoresho cya tekiniki cyubaka kigira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo.

Kwibira cyane

Adam (Adaptive Moment Estimation), yatangijwe na Kingma na Ba muri 2014, ihuza ibitekerezo bibiri. Ubwa mbere, umuvuduko: ituma impuzandengo yangirika yikigereranyo cya gradients zashize (umwanya wambere) bityo ivugurura ryubaka umuvuduko mubyerekezo bihamye. Icya kabiri, kuri buri kintu gipima: ikurikirana impuzandengo ya gradiyo ya kare (umwanya wa kabiri) kandi igabanya buri ntambwe kumuzi ya kare ya gaciro, bityo ibipimo hamwe nini nini, urusaku rufata intambwe ntoya kandi gake ivugururwa ifata intambwe nini. Guhuza n'imihindagurikire y'ikirere bivuze ko ushobora gukoresha igipimo kimwe cyo kwiga kumurongo wose. Impinduka, AdamW, ikuramo uburemere bwangirika kuva buhoro buhoro kandi byabaye nkibisanzwe byo guhugura impinduka nini nicyitegererezo cyururimi.

Ubushishozi

Adam agumana impuzandengo ebyiri zo kwiruka kuri buri kintu: m (gradients) na v (kwaduka kwaduka), ivugururwa nigipimo cyangirika beta1 (mubisanzwe 0.9) na beta2 (mubisanzwe 0,999). Kuberako byombi bitangirira kuri zeru, babogamye-bakosowe no kugabana na (1 - beta ^ t). Ivugurura ni theta = theta - lr * m_hat / (sqrt (v_hat) + epsilon), aho epsilon (hafi 1e-8) irinda kugabana na zeru. Niyo mpamvu Adamu akeneye kwiga bike-igipimo cyo kugereranya ugereranije na SGD isanzwe.

Kumenya Adamu na Optimizers

Adam ni akazi keza cyane inyuma yimiyoboro myinshi igezweho, ihita ihuza igipimo cyo kwiga kuri buri kintu cyose. Nibyingenzi kuko ituma imyitozo yimbitse yihuta kandi ntigabanuke cyane kuruta kumanuka gahoro gahoro. Adam na Adaptive Optimizers nigikoresho cya tekiniki cyubaka kigira ingaruka kumiterere yicyitegererezo, igiciro cyibikorwa remezo, ubukererwe, no kwizerwa mubipimo. Kugirango wubake byimbitse, fata Adam na Adaptive Optimizers nkicyitegererezo gikora, ntabwo ari ikintu kimwe: gusobanura ibyagezweho, gusobanura ibitekerezo, no gutandukanya ibyo sisitemu ishobora gukora byizewe nibisaba guca imanza zinzobere.

Mu myitozo, amakipe akomeye akoresha Adam na Adaptive Optimizers atezimbere ubwubatsi, amakuru, hamwe nibikorwa remezo birwanya kwizerwa nigiciro. Bandika ibipimo ngenderwaho byerekana intsinzi, bagerageza kurwanya amakuru afatika hamwe nakazi keza, kandi bagasubiramo bashingiye kubikorwa byagaragaye ko batsinzwe aho gutsinda inshuro imwe. Aha niho imyumvire yubumenyi ihinduka mubushobozi burambye kubicuruzwa, politiki, nibikorwa.

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mugihe kimwe, Guhindura igipimo kimwe gishobora guhisha intege nke za sisitemu. Uburyo bukomeye cyane ni uguhuza umuvuduko wikigereranyo hamwe na disipuline yimiyoborere: kuyobora abaderevu, gufata ibimenyetso, gutangaza ibyemezo byicyemezo, no gukomeza kuvugurura uburyo bwo kwirinda nkimyitwarire yicyitegererezo, ibyo abakoresha bategereje, nibisabwa n'amategeko bigenda bihinduka.

Ingaruka z'Ingamba

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka.

Ibyemezo byubwubatsi bitwara imikorere nigiciro cyimikorere kumyaka. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa.

Ubuhanga bwa tekinike bufasha amakipe guhitamo umurongo ukwiye, ntabwo ari shyashya gusa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa.

Guhitamo neza bya injeniyeri bigabanya ibintu byizewe mubikorwa. Mubikorwa byujuje ubuziranenge, ibi bihindurwa mumategeko agenga imikorere, imipaka nyirubwite, hamwe n'imihango yo gusubiramo kenshi kugirango amakipe ashobore kwigirira ikizere aho gupima ibidasobanutse.

Ejo hazaza ha Adamu na Optimizers

Adam na AdamW bakomeje kwiganza, ariko ubushakashatsi burimo gukora neza kuri moderi ya tiriyari-parameter, aho kubika indangagaciro ebyiri ziyongera kuburemere birahenze. Ibikoresho byo kwibuka-urumuri nka Adafactor, 8-bit ya Adam, hamwe na optimizers nshya nka Ntare (ikoresha imbaraga zishingiye gusa ku kimenyetso) na Sophia bagamije guhuza ubuziranenge bwa Adamu nibuke buke cyangwa guhuza byihuse. Tegereza uburyo bwo guhuza n'imihindagurikire y'ikirere bwateguwe neza kugira ngo bukwirakwizwe, amahugurwa make-yo gukomeza kugira ngo akomeze gutera imbere.

Gushyira mu bikorwa Isi

Guhugura indimi nini nka GPT na Llama, zikoresha AdamW nka optimizer isanzwe.

Kuringaniza neza ibishushanyo mbonera byateganijwe (urugero, ResNet) kuri dataset yihariye hamwe nigipimo cyambere cyo kwiga cya Adamu.

Kumenyereza ikwirakwizwa rya moderi inyuma ya generator zishusho nka Diffusion Stable.

Gukoresha 8-bit ya Adam mumasomero nka bitsandbytes kugirango uhuze optimizer leta mububiko buke bwa GPU.

Uburyo bwo Gushyira mu bikorwa

Adam na Adaptive Optimizers mubikorwa

Guhugura indimi nini nka GPT na Llama, zikoresha AdamW nka optimizer isanzwe.

Guhugura imvugo nini yindimi nka GPT na Llama, zikoresha AdamW nkibisanzwe bya optimizer Amakipe asanzwe abona ibisubizo byiza mugihe asobanura ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe.

Adam na Adaptive Optimizers mubikorwa

Kuringaniza neza ibishushanyo mbonera byateganijwe (urugero, ResNet) kuri dataset yihariye hamwe nigipimo cyambere cyo kwiga cya Adamu.

Kuringaniza neza ibishushanyo mbonera byateganijwe (urugero, ResNet) kuri dataset yihariye hamwe nigipimo gisanzwe cyo kwiga cya Adamu Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo byujuje ubuziranenge imbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.

Adam na Adaptive Optimizers mubikorwa

Kumenyereza ikwirakwizwa rya moderi inyuma ya generator zishusho nka Diffusion Stable.

Kumenyereza ikwirakwizwa ryikwirakwizwa ryamashusho nka Amakipe ahamye ya Diffusion Ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamuka kwabantu kubibazo, kandi akurikirana inyungu zibyara umusaruro nibiciro byigihe.

Adam na Adaptive Optimizers mubikorwa

Gukoresha 8-bit ya Adam mumasomero nka bitsandbytes kugirango uhuze optimizer leta mububiko buke bwa GPU.

Gukoresha 8-bit ya Adam mumasomero nka bitsandbytes kugirango uhuze na optimizer muri make ya GPU yibuka Amakipe ubusanzwe abona ibisubizo byiza iyo asobanuye ibipimo ngenderwaho byimbere, agakomeza inzira yo kuzamura abantu kubibazo byimbere, kandi akurikirana inyungu zibyara umusaruro nibiciro byamakosa mugihe.

Ingaruka & Kurinda

!

Gutezimbere igipimo kimwe gishobora guhisha intege nke za sisitemu.

!

Ibikorwa Remezo no kubungabunga akenshi usanga bidahabwa agaciro.

!

Icyuho cyumutekano no kwitegereza birashobora kwiyongera uko sisitemu igenda igorana.

Igishushanyo mbonera

1

Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa.

Sobanura ubukererwe, ubuziranenge, nigiciro cyibiciro mbere yo kubishyira mubikorwa. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

2

Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere.

Ibipimo byerekana umutwaro ufatika hamwe namakuru yimiterere. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

3

Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha.

Gukurikirana ibikoresho kubikosa, drift, ningaruka zabakoresha. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

4

Tegura inzira yo gusubiza ibyabaye mbere yo gupima.

Tegura inzira yo gusubiza ibyabaye mbere yo gupima. Fata buri ntambwe nk irembo ryibimenyetso: niba ibipimo bitujujwe, hagarika kuzenguruka, funga icyuho, hanyuma noneho wagure imikoreshereze.

Komeza Ubushakashatsi