--- language: - uz license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:4737 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: BAAI/bge-m3 widget: - source_sentence: Neustoyka to‘lash masalalari qaysi bo‘limda ko‘rib chiqiladi? sentences: - "Muddatli mehnat shartnomasi muddatidan oldin bekor qilingan taqdirda ushbu shartnomada\ \ \ntaraflarning neustoyka to‘lash haqidagi o‘zaro majburiyati nazarda tutilishi\ \ mumkin bo‘lib, unga \nbinoan, agar yakka tartibdagi mehnatga oid munosabatlar\ \ xodimning aybli harakatlari (harakatsizligi) \nbilan bog‘liq bo‘lmagan asoslar\ \ bo‘yicha ish beruvchining tashabbusiga ko‘ra tugatilgan bo‘lsa, ish \nberuvchi\ \ xodimga neustoyka to‘laydi, agar yakka tartibdagi mehnatga oid munosabatlar\ \ xodimning \ntashabbusiga ko‘ra, shuningdek xodi mning aybli harakatlari (harakatsizligi)\ \ bilan bog‘liq asoslar \nbo‘yicha tugatilgan bo‘lsa, xodim ish beruvchiga neustoyka\ \ to‘laydi. Agar mehnat shartnomasida \nneustoykaning miqdori belgilanmagan bo‘lsa,\ \ taraflar uni to‘lashdan ozod etiladi. \nMuddatli mehnat shartnomasi muddatidan\ \ oldin bekor qilinganda neustoykaning miqdori \nish beruvchi tomonidan xodimning\ \ manfaatlarini ko‘zlab qilingan xarajatlarga, xodim ishlab bergan \ndavrga va\ \ boshqa holatlarga qarab farqlanishi mumkin. \nMuddatli mehnat shartnomasi muddatid\ \ an oldin bekor qilinganda xodim tomonidan \nto‘lanadigan neustoyka miqdori ish\ \ beruvchi to‘laydigan neustoyka miqdoridan oshib ketishi mumkin \nemas. \nAgar\ \ mehnat shartnomasi ushbu Kodeks 160 -moddasining sakkizinchi qismida nazarda\ \ \ntutilgan hollarda xodimning tashabbusiga ko‘ra muddatidan oldin bekor qilingan\ \ bo‘lsa, u \nneustoykani to‘lashdan ozod etiladi. \nTaraflardan biri neustoykani\ \ to‘lashni rad etgan taqdirda, uni undirish sud tartibida amalga \noshiriladi." - "Mehnat nizolari bo‘yicha komissiya xodimning arizasini qabul qilishni, agar mehnat\ \ nizolari \nbo‘yicha komissiyaning yoki sudning ish yurituvida xuddi shu taraflar\ \ o‘rtasidagi nizo bo‘yicha, \nxuddi shu predmet va xuddi shu asoslar bo‘yicha\ \ boshqa ariza mavjud bo‘lsa yoxud ariza xodimning \nnomidan buning uchun vakolatli\ \ bo‘lmagan sh axs tomonidan berilgan bo‘lsa yoki ushbu yakka \ntartibdagi mehnat\ \ nizosini ko‘rib chiqish komissiyaning vakolatlariga kirmasa, rad etadi. \n\ Avvalgi majlisda tayinlangan mehnat nizolari bo‘yicha komissiya raisi ariza beruvchiga\ \ \narizani qabul qilishga doir yoz ma ravishda asoslantirilgan rad javobini uch\ \ kunlik muddat ichida \nberadi." - "taalluqliligi (bo‘ysunuvi) o‘zgarganligi munosabati bilan ishni davom ettirishni\ \ rad etganligi \nmunosabati bilan. \nIshdan bo‘shatish nafaqasining miqdori mazkur\ \ ish beruvchidagi ish stajiga bog‘liq bo‘ladi \nva u: \nuch yilgacha ish stajiga\ \ ega bo‘lgan xodimlar uchun — o‘rtacha oylik ish haqining ellik \nfoizidan; \n\ uch yildan besh yilgacha ish stajiga ega bo‘lgan xodimlar uch un — o‘rtacha oylik\ \ ish \nhaqining yetmish besh foizidan; \nbesh yildan o‘n yilgacha ish stajiga\ \ ega bo‘lgan xodimlar uchun — o‘rtacha oylik ish \nhaqining yuz foizidan; \n\ o‘n yildan o‘n besh yilgacha ish stajiga ega bo‘lgan xodimlar uchun — o‘rtacha\ \ oylik ish \nhaqining bir yuz ellik foizidan; \no‘n besh yildan ortiq ish stajiga\ \ ega bo‘lgan xodimlar uchun — o‘rtacha oylik ish haqining \nikki yuz foizidan\ \ kam bo‘lishi mumkin emas. \nJamoa kelishuvlarida, shuningdek jamoa shartnomasida,\ \ ichki hujjatlarda, mehnat \nshartnomasida xodimlarga ish beruvchining mablag‘lari\ \ hisobidan ishdan bo‘shatish nafaqasini \nto‘lash chog‘ida qo‘shimcha kafolatlar\ \ (ushbu moddaning uchinchi qismida mustahkamlanganlariga \nnisbatan ishdan bo‘shatish\ \ nafa qasining oshirilgan miqdorlari, ishdan bo‘shatish nafaqasining \nmiqdoriga\ \ ta’sir ko‘rsatadigan ish stajiga xodimlarning muayyan tarmoqdagi yoki muayyan\ \ kasbga doir mehnat faoliyati davrlarini kiritish, ushbu tashkilotga ish beruvchining\ \ taklifi bilan ishga kirgan \nxodimlarning ko‘rsatilgan stajida xodim ilgari\ \ mehnat qilgan tashkilotda ishlagan vaqtni hisobga \nolish), belgilanishi mumkin.\ \ \nXodimning aybli harakatlari (harakatsizligi) bilan bog‘liq bo‘lgan asoslarga\ \ ko‘ra xodimlar \nbilan mehnat shartnomasi bekor qilingan taqdirda jamoa kelishuvlarida,\ \ shuningdek jamoa \nshartnomasida, ichki hujjatlarda, mehnat shartnomasida yoxud\ \ ish beruvchining, yuridik shaxs" - source_sentence: Tarmoq va hududiy darajadagi ijtimoiy sheriklikning xususiyatlari qanday? sentences: - "Xizmat tekshiruvi o‘tkazish uchun ish beruvchining buyrug‘i bilan xizmat tekshiruvi\ \ \no‘tkazish bo‘yicha komissiya tuziladi (bundan buyon matnda komissiya deb yuritiladi).\ \ \nKomissiya kamida uch nafar a’zodan iborat bo‘lishi kerak, ularning bir nafari\ \ komissiyaning \nraisi bo‘ladi. Komissiya tarkibiga tashkilotda mavjud bo‘lgan\ \ taqdirda kasaba uyushmasi \nqo‘mitasining a’zosi kiradi. Komissiya raisi komissiya\ \ ishini tashkil etadi va muvofiqlashtiradi. \nUning o‘tkazilayotgan xizmat tekshiruvi\ \ doirasidagi qonuniy talablari komissiya a’zolari tomonidan \nbajarilishi majburiydir.\ \ Komissiya raisi xizmat tekshiruvini tashkil etish, tayyorlash va o‘tkazish \n\ sifati, uning natijalari, xulosalari va takliflarining xolisligi uchun shaxsan\ \ javobgar bo‘ladi. \nKomissiya tarkibiga quyidagi shaxslarning kiritilishiga\ \ yo‘l qo‘yilmaydi: \nxizmat tekshiruvi o‘tkazish to‘g‘risida qaror qabul qilgan\ \ mansabdor shaxs; \nharakatlari tekshirilishi zarur bo‘lgan xodimlar bo‘ysunuvidagi\ \ xodimlar; \no‘ziga nisbatan xizmat teks hiruvi o‘tkazilayotgan xodim bilan qarindoshlik\ \ aloqalarida \nbo‘lgan shaxslar; \nxizmat tekshiruvi natijalaridan bevosita yoki\ \ bilvosita manfaatdor bo‘lishi mumkin bo‘lgan \nshaxslar, shu jumladan xodim\ \ tomonidan intizomiy qilmish sodir etilishiga yoki intizomi y \nqilmishning yashirilishiga\ \ daxldor ekanligi to‘g‘risida asoslangan gumonlar mavjud bo‘lgan shaxslar; \n\ murojaati xizmat tekshiruvi o‘tkazilishi uchun asos bo‘lib xizmat qilgan shaxslar;\ \ \no‘ziga nisbatan xizmat tekshiruvi o‘tkazilayotgan xodimlar. \nXizmat tekshiruvini\ \ o‘tkazishga maxsus bilimlar sohasida maslahat olish uchun shartnoma \nasosida\ \ ekspertlar sifatida mutaxassislar jalb qilinishi mumkin. 305-modda. Komissiyaning\ \ huquq va majburiyatlari \nKomissiya quyidagi huquqlarga ega: \no‘ziga nisbatan\ \ xizmat tekshiruvi o‘tkazilayotgan xodimlarga yozma shaklda tushuntirishlar" - "Jamoa shartnomasida, boshqa ichki hujjatlarda, mehnat shartnomasida yoki xodim\ \ va ish \nberuvchi o‘rtasidagi kelishuvga ko‘ra mehnat shartnomasini bekor qilish\ \ chog ‘ida (bundan mehnat \nshartnomasi xodimning aybli harakatlari (harakatsizligi)\ \ uchun bekor qilingan hollar mustasno) \nfoydalanilmagan har yilgi mehnat ta’tillarini\ \ keyinchalik mehnatga oid munosabatlarni tugatgan \nholda xodimning yozma arizasi\ \ asosida berish nazarda tutilishi mumkin. \nMehnat shartnomasini uning muddati\ \ tugashi munosabati bilan bekor qilish chog‘ida \nkeyinchalik mehnat shartnomasini\ \ bekor qilgan holdagi ta’til har yilgi mehnat ta’tilining vaqti ushbu \nshartnoma\ \ muddatining chegarasidan to‘liq yoki qisman chiqib ketganda ham berilishi mumkin.\ \ \nUshbu moddaning birinchi va ikkinchi qismlarida nazarda tutilgan hollarda\ \ har yilgi mehnat \nta’tilining oxirgi kuni mehnat shartnomasi bekor qilinadigan\ \ kun deb hisoblanadi. \nXodimning tashabbusiga ko‘ra keyinchalik mehnat shartnomasini\ \ bekor qilgan holda har \nyilgi mehnat ta’tilini berish chog‘ida ushbu xodim\ \ mehnat shartnomasini bekor qilish to‘g‘risidagi \narizasini o‘zining mehnat\ \ ta’tili boshlanadigan kunga qadar chaqirib olish huquqiga ega. \n5-§. Ijtimoiy\ \ ta’tillar" - "Tarmoq va hududiy darajalardagi ijtimoiy sheriklik ikki tomonlama yoki uch tomonlama\ \ \nxususiyatga ega. Xodimlar va ish beruvchilarning tegishli birlashmalari tarmoq\ \ va hududiy darajadagi \nikki tomonlama ijtimoi y sheriklik taraflaridir. Hududiy\ \ darajadagi uch tomonlama ijtimoiy \nsheriklikda xodimlar va ish beruvchilar\ \ hududiy birlashmalarining taklifiga ko‘ra mahalliy ijro \netuvchi hokimiyat\ \ organlari va boshqa manfaatdor davlat organlari ishtirok etadi. Tarmoq \ndarajasidagi\ \ uch tomonlama ijtimoiy sheriklikda xodimlarning va ish beruvchilarning tarmoq\ \ \nbirlashmalari taklifiga ko‘ra tegishli tarmoqdagi davlat boshqaruvi organlari\ \ ishtirok etadi. \nO‘zbekiston Respublikasi Bandlik va mehnat munosabatlari vazirligi\ \ tegishl i tarmoqdagi davlat \nboshqaruvi organlari ish beruvchilar sifatida\ \ ishtirok etadigan hollarda tarmoq darajasidagi uch \ntomonlama ijtimoiy sheriklikda\ \ ishtirok etadi. \nOldingi tahrirga qarang. \nRespublika darajasidagi ijtimoiy\ \ sheriklik uch tomonlama xususiyatga ega. Xodimlar va ish \nberuvchilarning respublika\ \ birlashmalari hamda O‘zbekiston Respublikasi Vazirlar Mahkamasi, \nmanfaatdor\ \ vazirliklar va idoralar respublika darajasidagi ijtimoiy sheriklik taraflaridir.\ \ \n(39-moddaning uchinchi qismi O‘zbekiston Respublikasining 2023 -yil 28-noyabrdagi\ \ O‘RQ-880-\nsonli Qonuni tahririda — Qonunchilik ma’lumotlari milliy bazasi,\ \ 29.11.2023-y., 03/23/880/0905-son) \nMahalliy ijro etuvchi hokimiyat organlari\ \ ish beruvchilar sifatida ish yuritadigan hollarda \nular ijtimoiy sheriklikning\ \ ish beruvchiga vakillik qiladigan tarafi bo‘ladi." - source_sentence: Mehnat shartnomasi asosida xodimlar uchun ta’tillarning qanday turlari mavjud? sentences: - "Nogironligi bo‘lgan xodimlarni xizmat safariga yuborishga, tungi ishlarga, ish\ \ vaqtidan \ntashqari ishlarga hamda dam olish va ishlanmaydigan bayram kunlaridagi\ \ ishlarga jalb qilishga faqat \nularning roziligi bilan, agar ushbu xodimlar\ \ uchun bunday ishlar tibbiy -ijtimoiy ekspert komissiyasi \ntavsiyalarida taqiqlanmagan\ \ bo‘lsa, yo‘l qo‘yiladi." - "Ushbu Kodeksda ish beruvchi bilan tuzilgan mehnat shartnomasi asosida mehnat\ \ faoliyatini \namalga oshirayotgan xodimlar uchun ta’tillarning quyidagi turlari\ \ nazarda tutilgan: \nhar yilgi mehnat ta’tili; \nijtimoiy ta’tillar; \nish haqi\ \ qisman saqlanadigan ta’til; \nish haqi saqlanmaydigan ta’til." - "taqdirda, mehnat shartnom asining barcha nusxalarida mansabdor shaxsning imzosi\ \ muhr bilan \ntasdiqlanadi. Qo‘shimcha kelishuvning bir nusxasi xodimga beriladi,\ \ boshqasi (boshqalari) ish \nberuvchida mehnat shartnomasi bilan birga saqlanadi.\ \ Xodim tomonidan qo‘shimcha kelishuvning \nnusxasi olinganligi xodimning ish\ \ beruvchida saqlanadigan qo‘shimcha kelishuvning nusxasiga \nqo‘yilgan qo‘shimcha\ \ imzosi bilan tasdiqlanadi. \nXodimni doimiy boshqa ishga o‘tkazish, mehnat shartnomasida\ \ nazarda tutilgan mehnat \nshartlarini o‘zgartirish, shuningdek mehnat shartnomasida\ \ shart qilib ko‘rsatilgan ish joyini \no‘zgartirish to‘g‘risidagi buyruqlar mehnat\ \ shartnomasi taraflari tomonidan qo‘shimcha kelishuv \ntuzish orqali ushbu shartnomaga\ \ kiritilgan o‘zgartishlarning mazmuniga aynan muvofiq ravishda \nchiqariladi\ \ va xodimga imzo qo‘ydirib e’lon qilinadi. \nXodimni vaqtincha boshqa ishga\ \ o‘tkazish o‘tkazishning muddati ko‘rsatilgan holda buyruq \nbilan rasmiylashtiriladi.\ \ \nMehnat shartnomasi taraflarining kelishuviga ko‘ra va xodimning tashabbusi\ \ bilan xodimni \nvaqtincha boshqa ishga o‘tkazish to‘g‘risida buyruq chiqarish\ \ uchun xodimning yozma arizasi asos \nbo‘ladi. \nXodim sog‘lig‘ining holatiga\ \ ko‘ra xodimni vaqtincha boshqa ishga o‘tkazish, homilador \nayolni, shuningdek\ \ ikki yoshga to‘lmagan bolasini parvarishlayotgan ota-onadan birini (vasiyni)\ \ \nularning avvalgi ishni bajarish imkoniyati bo‘lmagan taqdirda vaqtincha boshqa\ \ ishga o‘tkazish \nhaqida buyruq chiqarish uchun ularning arizasi va tibbiy xulosa\ \ asos bo‘ladi. \nIsh beruvchining tashabbusiga ko‘ra xodimni vaqtincha boshqa\ \ ishga o‘tkazish to‘g‘risida \nbuyruq chiqarish uchun ishlab chiqarish zaruriyati\ \ yoki bekor turib qolish faktlarining mavjudligi \nasos bo‘ladi. \nXodimni vaqtincha\ \ boshqa ishga o‘tkazish mehnat shartnomasida aks ettirilmaydi." - source_sentence: Mehnat shartnomasida nazarda tutilmagan zararli sharoitlarda ish bajarish rad etilganda qanday huquq mavjud? {chapter} va {section} ga ko‘ra. sentences: - "Tartibga solinadigan munosabatlar sohasiga qarab hududiy, tarmoq va bosh jamoa\ \ \nkelishuvlari tuzilishi mumkin. \nHududiy va tarmoq jamoa kel ishuvlari ikki\ \ tomonlama yoki uch tomonlama bo‘lishi \nmumkin. \nIkki tomonlama jamoa kelishuvlari\ \ ushbu Kodeksning 42 va 46-moddalarida ko‘rsatilgan \nxodimlarning hamda ish\ \ beruvchilarning vakolatli vakillari o‘rtasida tuziladi. \nUch tomonlama jamoa\ \ kelishuvlari ushbu Kodeks 42 va 46-moddalarining ikkinchi qismida \nko‘rsatilgan\ \ xodimlarning hamda ish beruvchilarning vakolatli vakillari va tegishli ijro\ \ etuvchi \nhokimiyat organi o‘rtasida tuziladi. Bunda ijro etuvchi hokimiyat\ \ organining ishtirok etishi xodimlar \nva ish beruvchilar vakolatli vakillarining\ \ taklifiga ko‘ra belgilanadi. \nBajarilishining moliyaviy ta’minoti tegishli\ \ budjetlar mablag‘lari hisobidan amalga \noshiriladigan majburiyatlarni o‘z ichiga\ \ olgan jamoa kelishuvlari tegishli vakolatli organning roziligi \nmavjud bo‘lgan\ \ taqdirda tuziladi. \nBosh jamoa kelishuvi uch tomonlama bo‘ladi hamda xodimlar\ \ va ish beruvchilarning \nrespublika darajasidagi vakolatli vakillari hamda O‘zbekiston\ \ Respublikasi Vazirlar Mahkamasi \no‘rtasida tuziladi. \nXodimlarning vakillari\ \ ish beruvchi yoki ish beruvchining vakili bo‘lmagan ijro etuvc hi \nhokimiyat\ \ organidan ular bilan ikki tomonlama kelishuv tuzishni talab qilishga haqli emas." - "Davlat xodimlarga mehnatni muhofaza qilish talablariga mos keladigan sharoitlarda\ \ mehnat \nqilish huquqi himoya qilinishini kafolatlaydi. \nMehnat shartnomasida\ \ nazarda tutilgan mehnat sharoitlari mehnatni muhofaza qilish \ntalablariga mos\ \ kelishi kerak. \nMehnatni muhofaza qilishga doir talablar buzilganligi tufayli\ \ ish beruvchining faoliyati \nto‘xtatilgan vaqtda xodimning ish joyi (lavozimi)\ \ va o‘rtacha ish haqi saqlab qolinadi. Bu vaqtda \nxodim bajarayotgan ishi bo‘yicha\ \ mehnatiga haq to‘langan holda, lekin avvalgi ish bo‘yicha o‘rtacha \nish haqidan\ \ kam bo‘lmagan miqdorda haq to‘langan holda o‘z roziligi bilan ish beruvchi tomonidan\ \ \nboshqa ishga o‘tkazilishi mumkin. \nXodim o‘z hayoti va sog‘lig‘i uchun xavf\ \ yuzaga kelganda ishni bajarishni rad etgan \ntaqdirda, ish beruvchi bunday xavf\ \ bartaraf etilguniga qadar xodimga boshqa ish berishi shart. \nAgar xodimga obyektiv\ \ sabablarga ko‘ra boshqa ish berishning imkoni bo‘lmasa, xodimning \no‘z hayoti\ \ va sog‘lig‘i uchun xavf bartaraf etilguni ga qadar bekor turib qolgan vaqti\ \ uchun ish \nberuvchi tomonidan ushbu Kodeks 266-moddasining ikkinchi qismiga\ \ muvofiq haq to‘lanadi. \nXodim belgilangan normalarga muvofiq shaxsiy va jamoaviy\ \ himoya vositalari b ilan \nta’minlanmagan taqdirda, ish beruvchi xodimdan mehnat\ \ majburiyatlarini bajarishni talab qilishga \nhaqli emas va shu sababdan ishda\ \ yuzaga kelgan bekor turib qolganlik uchun ushbu Kodeks 266 -\nmoddasining ikkinchi\ \ qismiga muvofiq haq to‘lashi shart. \nXodimning mehnatni muhofaza qilish talablari\ \ buzilganligi oqibatida o‘z hayotiga va \nsog‘lig‘iga xavf yuzaga kelgan taqdirda\ \ yoxud mehnat shartnomasida nazarda tutilmagan zararli va \n(yoki) xavfli mehnat\ \ sharoitlarida ishlarni bajarishni rad etishi uni intizomiy javobgarlikka tortishga\ \ \nsabab bo‘lmaydi. \nXodimning o‘z mehnat majburiyatlarini bajarishi munosabati\ \ bilan hayotiga va sog‘lig‘iga" - "Mehnat huquqlari va majburiyatlariga ega bo‘lish layoqati (mehnatga oid huquq\ \ layoqati) \nhamda fuqaroning (jismoniy shaxsning) o‘z xatti -harakatlari orqali\ \ mehnat huquqlariga ega bo‘lish \nva ularni amal ga oshirish, o‘zi uchun mehnat\ \ majburiyatlarini olish va ularni bajarish layoqati \n(mehnatga oid muomala layoqati)\ \ O‘zbekiston Respublikasining barcha fuqarolari uchun teng \nravishda e’tirof\ \ etiladi. \nChet el fuqarolari, fuqaroligi bo‘lmagan shaxslar, agar O ‘zbekiston\ \ Respublikasining \nqonunchiligida yoki xalqaro shartnomasida boshqacha qoida\ \ nazarda tutilmagan bo‘lsa, xuddi \nO‘zbekiston Respublikasi fuqarolari ega bo‘lgan\ \ mehnatga oid huquq layoqatiga va muomala \nlayoqatiga ega bo‘ladi. \nXodimning\ \ mehnatga oid h uquq layoqati va muomala layoqati u o‘n olti yoshga to‘lgan \n\ paytidan e’tiboran bir vaqtning o‘zida vujudga keladi, bundan ushbu Kodeksda va\ \ boshqa qonunlarda \nnazarda tutilgan hollar mustasno." - source_sentence: Intizomiy jazolar qanday qo'llaniladi? sentences: - "hodisa sodir bo‘lganiga uch yildan oshgan bo‘lsa, shartnoma nomuayyan muddatga\ \ uzaytirilgan deb \nhisoblanadi. \nNomuayyan muddatga tuzilgan mehnat shartnomasi\ \ xodimning roziligisiz belgilangan \nmuddatga qayta tuzilishi mumkin emas. \n\ Agar qonunda boshq acha qoida nazarda tutilmagan bo‘lsa, muddatli mehnat \nshartnomasining\ \ muddati tugaganidan keyin, ushbu Kodeksning 112 yoki 113-moddasida nazarda \n\ tutilgan asoslar mavjud bo‘lganda taraflar uning amal qilish muddatini uzaytirishga\ \ haqli. Bunda \nmuddatli mehnat shartnomasining jami muddati besh yildan oshmasligi\ \ kerak. Agar muddatli mehnat \nshartnomasining umumiy muddati u uzaytirilishidan\ \ oldin va keyin besh yildan o shgan bo‘lsa, \nmehnat shartnomasi nomuayyan muddatga\ \ tuzilgan deb topiladi, bundan qonunda nazarda tutilgan \nhollar mustasno. \n\ O‘zi bilan nomuayyan muddatga mehnat shartnomasi tuzilayotgan xodimlar uchun nazarda\ \ \ntutilgan huquqlar va kafolatlarni berishdan bosh tortish maqsadida muddatli\ \ mehnat shartnomalarini \ntuzish taqiqlanadi. \nYakka tartibdagi mehnat nizolarini\ \ ko‘rib chiqish chog‘ida muddatli mehnat shartnomasini \ntuzishning asosliligini\ \ isbotlash vazifasi ish beruvchining zimmasiga yuklatiladi." - "Ushbu Kodeksda nazarda tuti lgan asoslardan tashqari, O‘zbekiston Respublikasi\ \ hududida \nmehnat faoliyatini amalga oshirish huquqiga doir tasdiqnomaning amal\ \ qilish muddati tugatilganligi \nyoki bekor qilinganligi chet el fuqarosi bilan\ \ tuzilgan mehnat shartnomasini bekor qilish uchun a sos \nbo‘ladi. \nO‘zbekiston\ \ Respublikasi hududida mehnat faoliyatini amalga oshirish huquqiga doir \ntasdiqnomaning\ \ amal qilish muddati tugashi munosabati bilan uning amal qilish muddati tugagan\ \ \nkunda mehnat shartnomasi bekor qilinishi lozim. \nO‘zbekiston Resp ublikasi\ \ hududida mehnat faoliyatini amalga oshirish huquqiga doir \ntasdiqnoma bekor\ \ qilinganda mehnat shartnomasi ish beruvchi O‘zbekiston Respublikasi Bandlik\ \ va \nmehnat munosabatlari vazirligi huzuridagi Tashqi mehnat migratsiyasi agentligining\ \ tegishli \nxabarnomasini olgan kunda bekor qilinishi lozim." - "Intizomiy javobgarlik xodim tomonidan intizomiy qilmish (ushbu Kodeks 301-moddasining\ \ \nikkinchi qismi) sodir etilganligi uchun yuzaga keladigan va ushbu xodimga\ \ nisbatan intizomiy jazo \nchorasi qo‘llanilishida ifodalanadigan yuridik javobgarlikdir.\ \ \nIntizomiy javobgarlikning turlari umumiy va maxsus intizomiy javobgarlikdan\ \ iboratdir. \nUmumiy intizomiy javobgarlik ushbu Kodeks va ichki mehnat tartibi\ \ qoidalari bilan tartibga \nsolinadigan javobgarlik bo‘lib, u xodimga nisbatan\ \ ushbu Kodeksning 312-moddasida nazarda \ntutilgan intizomiy jazo choralaridan\ \ birini qo‘llashdan iborat va barcha xodimlarga nisbatan tatbiq \netiladi, bundan\ \ o‘zi uchun maxsus intizomiy javobgarlik belgilangan shaxslar mustasno. \nMaxsus\ \ intizomiy javobgarlik xodimlarning faqat alohida toifalari uchun qonunda, \n\ shuningdek intizom to‘g‘risidagi ustavlar va nizomlarda nazarda tutilgan hamda\ \ xodimga nisbatan tegishli qonunda, intizom haqidagi ustavda va nizomda nazarda\ \ tutilgan intizomi y choralarni \nqo‘llashdan iborat javobgarlikdir." pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: BGE m3 Uzbek Legal Matryoshka results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 1024 type: dim_1024 metrics: - type: cosine_accuracy@1 value: 0.49146110056925996 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8178368121442126 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8956356736242884 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9468690702087287 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.49146110056925996 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2726122707147375 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1791271347248577 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09468690702087286 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.49146110056925996 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8178368121442126 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8956356736242884 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9468690702087287 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7326456943688795 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6620523478208482 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6645722072183388 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.4838709677419355 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8083491461100569 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8918406072106262 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9430740037950665 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4838709677419355 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.26944971537001894 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17836812144212524 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09430740037950665 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.4838709677419355 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8083491461100569 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8918406072106262 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9430740037950665 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7267788063618378 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6555984759495188 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6584413328007779 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.4857685009487666 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8026565464895635 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8842504743833017 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9430740037950665 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4857685009487666 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2675521821631878 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17685009487666034 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09430740037950665 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.4857685009487666 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8026565464895635 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8842504743833017 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9430740037950665 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7244666028489126 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6529012680340948 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6554696255404289 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.4686907020872865 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.7893738140417458 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8804554079696395 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.937381404174573 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4686907020872865 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2631246046805819 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17609108159392792 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09373814041745732 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.4686907020872865 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.7893738140417458 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8804554079696395 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.937381404174573 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7119654489015288 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6382149634047163 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6411064521465707 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.4667931688804554 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.7836812144212524 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.8652751423149905 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9278937381404174 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4667931688804554 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.26122707147375074 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17305502846299808 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09278937381404176 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.4667931688804554 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.7836812144212524 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.8652751423149905 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9278937381404174 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7054923905280535 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6328469022017404 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.636233848811519 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.4819734345351044 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.7552182163187856 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.855787476280835 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9240986717267552 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4819734345351044 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.25173940543959517 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17115749525616697 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09240986717267553 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.4819734345351044 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.7552182163187856 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.855787476280835 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9240986717267552 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.7054873838678853 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6348250052709251 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6382566686394829 name: Cosine Map@100 --- # BGE m3 Uzbek Legal Matryoshka This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the json dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 1024 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - json - **Language:** uz - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("fitlemon/bge-m3-uz-legal-matryoshka") # Run inference sentences = [ "Intizomiy jazolar qanday qo'llaniladi?", 'Intizomiy javobgarlik xodim tomonidan intizomiy qilmish (ushbu Kodeks 301-moddasining \nikkinchi qismi) sodir etilganligi uchun yuzaga keladigan va ushbu xodimga nisbatan intizomiy jazo \nchorasi qo‘llanilishida ifodalanadigan yuridik javobgarlikdir. \nIntizomiy javobgarlikning turlari umumiy va maxsus intizomiy javobgarlikdan iboratdir. \nUmumiy intizomiy javobgarlik ushbu Kodeks va ichki mehnat tartibi qoidalari bilan tartibga \nsolinadigan javobgarlik bo‘lib, u xodimga nisbatan ushbu Kodeksning 312-moddasida nazarda \ntutilgan intizomiy jazo choralaridan birini qo‘llashdan iborat va barcha xodimlarga nisbatan tatbiq \netiladi, bundan o‘zi uchun maxsus intizomiy javobgarlik belgilangan shaxslar mustasno. \nMaxsus intizomiy javobgarlik xodimlarning faqat alohida toifalari uchun qonunda, \nshuningdek intizom to‘g‘risidagi ustavlar va nizomlarda nazarda tutilgan hamda xodimga nisbatan tegishli qonunda, intizom haqidagi ustavda va nizomda nazarda tutilgan intizomi y choralarni \nqo‘llashdan iborat javobgarlikdir.', 'Ushbu Kodeksda nazarda tuti lgan asoslardan tashqari, O‘zbekiston Respublikasi hududida \nmehnat faoliyatini amalga oshirish huquqiga doir tasdiqnomaning amal qilish muddati tugatilganligi \nyoki bekor qilinganligi chet el fuqarosi bilan tuzilgan mehnat shartnomasini bekor qilish uchun a sos \nbo‘ladi. \nO‘zbekiston Respublikasi hududida mehnat faoliyatini amalga oshirish huquqiga doir \ntasdiqnomaning amal qilish muddati tugashi munosabati bilan uning amal qilish muddati tugagan \nkunda mehnat shartnomasi bekor qilinishi lozim. \nO‘zbekiston Resp ublikasi hududida mehnat faoliyatini amalga oshirish huquqiga doir \ntasdiqnoma bekor qilinganda mehnat shartnomasi ish beruvchi O‘zbekiston Respublikasi Bandlik va \nmehnat munosabatlari vazirligi huzuridagi Tashqi mehnat migratsiyasi agentligining tegishli \nxabarnomasini olgan kunda bekor qilinishi lozim.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Information Retrieval * Datasets: `dim_1024`, `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | dim_1024 | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 | |:--------------------|:-----------|:-----------|:-----------|:----------|:-----------|:-----------| | cosine_accuracy@1 | 0.4915 | 0.4839 | 0.4858 | 0.4687 | 0.4668 | 0.482 | | cosine_accuracy@3 | 0.8178 | 0.8083 | 0.8027 | 0.7894 | 0.7837 | 0.7552 | | cosine_accuracy@5 | 0.8956 | 0.8918 | 0.8843 | 0.8805 | 0.8653 | 0.8558 | | cosine_accuracy@10 | 0.9469 | 0.9431 | 0.9431 | 0.9374 | 0.9279 | 0.9241 | | cosine_precision@1 | 0.4915 | 0.4839 | 0.4858 | 0.4687 | 0.4668 | 0.482 | | cosine_precision@3 | 0.2726 | 0.2694 | 0.2676 | 0.2631 | 0.2612 | 0.2517 | | cosine_precision@5 | 0.1791 | 0.1784 | 0.1769 | 0.1761 | 0.1731 | 0.1712 | | cosine_precision@10 | 0.0947 | 0.0943 | 0.0943 | 0.0937 | 0.0928 | 0.0924 | | cosine_recall@1 | 0.4915 | 0.4839 | 0.4858 | 0.4687 | 0.4668 | 0.482 | | cosine_recall@3 | 0.8178 | 0.8083 | 0.8027 | 0.7894 | 0.7837 | 0.7552 | | cosine_recall@5 | 0.8956 | 0.8918 | 0.8843 | 0.8805 | 0.8653 | 0.8558 | | cosine_recall@10 | 0.9469 | 0.9431 | 0.9431 | 0.9374 | 0.9279 | 0.9241 | | **cosine_ndcg@10** | **0.7326** | **0.7268** | **0.7245** | **0.712** | **0.7055** | **0.7055** | | cosine_mrr@10 | 0.6621 | 0.6556 | 0.6529 | 0.6382 | 0.6328 | 0.6348 | | cosine_map@100 | 0.6646 | 0.6584 | 0.6555 | 0.6411 | 0.6362 | 0.6383 | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 4,737 training samples * Columns: question and chunk * Approximate statistics based on the first 1000 samples: | | question | chunk | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | question | chunk | |:--------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Noqulay tabiiy-iqlim sharoitlaridagi ish uchun mehnatga haq to‘lash koeffitsiyentlari haqida {chapter} va {section}da nima deyiladi? | Noqulay tabiiy-iqlim sharoitlaridagi ish uchun mehnatga haq to‘lash koeffitsiyenti ayrim
hududlardagi mehnat sharoitlarining xususiyatlari inobatga olingan holda xodimlarga to‘lanadigan
kompensatsiya xususiyatiga ega bo‘lgan ustama turidir. Koeffitsiyentlarning eng kam miqdorlari va
ularni qo‘llash tartibi O‘zbekiston Respublikasi Vazirlar Mahkamasi tomonidan belgilanadi.
28-bob. Xodim mehnatining xususiyati bilan bog‘liq bo‘lgan mehnatni huquqiy jihatdan
tartibga solishning o‘ziga xos xususiyatlari
1-§. Tashkilot rahbarining, uning o‘rinbosarlarining, tashkilot bosh buxgalterining va
tashkilot alohida bo‘linmasi rahbarining mehnatini huquqiy jihatdan tartibga solishning
o‘ziga xos xususiyatlari | | Homiladorlik yoki farzandlar borligi bilan bog‘liq sabablarga ko‘ra ishga qabul qilmaslik qonunga xilofmi? | Ishga qabul qilishni qonunga xilof ravishda rad etishga yo‘l qo‘yilmaydi.
Quyidagilar ishga qabul qilishni qonunga xilof ravishda rad etishdir:
mehnat va mashg‘ulotlar sohasida kamsitishni taqiqlash to‘g‘risidagi talablarni buzish;
ish beruvchi tomonidan ishga taklif etilgan shaxslarni ishga qabul qilmaslik;
ish beruvchi qonunga muvofiq mehnat shartnomasini tuzishi shart bo‘lgan shaxslarni (ish
o‘rinlarining belgilangan eng k am soni hisobiga ishga yuborilgan shaxslarni, ish beruvchi alohida
asoslar bo‘yicha mehnat shartnomasini bekor qilgan shaxslarni, ular qayta ishga qabul qilingan
taqdirda va boshqalarni) ishga qabul qilmaslik; homiladorlik yoki farzandlar borligi bilan bog‘liq sabablarga ko‘ra ishga qabul qilmaslik;
Oldingi tahrirga qarang.
sudlanganligi, shu jumladan tugallangan va olib tashlangan sudlanganligi sababli shaxslarni
ishga qabul qi lmaslik, bundan qonunchilikda nazarda tutilgan hollar mustasno, yoxud shaxslarni
ularning qarindoshlari sudlanganligi, shu j... | | Xizmat safariga yuborish uchun nogironligi bo‘lgan xodimlarning roziligi qanday ahamiyatga ega {chapter} va {section}da? | Nogironligi bo‘lgan xodimlarni xizmat safariga yuborishga, tungi ishlarga, ish vaqtidan
tashqari ishlarga hamda dam olish va ishlanmaydigan bayram kunlaridagi ishlarga jalb qilishga faqat
ularning roziligi bilan, agar ushbu xodimlar uchun bunday ishlar tibbiy -ijtimoiy ekspert komissiyasi
tavsiyalarida taqiqlanmagan bo‘lsa, yo‘l qo‘yiladi. | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 1024, 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `fp16`: True - `tf32`: False - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: False - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch_fused - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs
Click to expand | Epoch | Step | Training Loss | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |:-------:|:--------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| | 0.0169 | 10 | 2.468 | - | - | - | - | - | - | | 0.0337 | 20 | 3.0476 | - | - | - | - | - | - | | 0.0506 | 30 | 2.0878 | - | - | - | - | - | - | | 0.0675 | 40 | 2.1392 | - | - | - | - | - | - | | 0.0843 | 50 | 2.3539 | - | - | - | - | - | - | | 0.1012 | 60 | 2.367 | - | - | - | - | - | - | | 0.1180 | 70 | 1.6277 | - | - | - | - | - | - | | 0.1349 | 80 | 2.0299 | - | - | - | - | - | - | | 0.1518 | 90 | 1.7242 | - | - | - | - | - | - | | 0.1686 | 100 | 1.5173 | - | - | - | - | - | - | | 0.1855 | 110 | 1.6598 | - | - | - | - | - | - | | 0.2024 | 120 | 1.0105 | - | - | - | - | - | - | | 0.2192 | 130 | 1.4555 | - | - | - | - | - | - | | 0.2361 | 140 | 0.3602 | - | - | - | - | - | - | | 0.2530 | 150 | 0.8921 | - | - | - | - | - | - | | 0.2698 | 160 | 0.6716 | - | - | - | - | - | - | | 0.2867 | 170 | 0.7469 | - | - | - | - | - | - | | 0.3035 | 180 | 1.0121 | - | - | - | - | - | - | | 0.3204 | 190 | 0.5142 | - | - | - | - | - | - | | 0.3373 | 200 | 3.1294 | - | - | - | - | - | - | | 0.3541 | 210 | 1.5231 | - | - | - | - | - | - | | 0.3710 | 220 | 0.8671 | - | - | - | - | - | - | | 0.3879 | 230 | 1.8561 | - | - | - | - | - | - | | 0.4047 | 240 | 1.3404 | - | - | - | - | - | - | | 0.4216 | 250 | 1.4122 | - | - | - | - | - | - | | 0.4384 | 260 | 1.1002 | - | - | - | - | - | - | | 0.4553 | 270 | 1.2149 | - | - | - | - | - | - | | 0.4722 | 280 | 2.1969 | - | - | - | - | - | - | | 0.4890 | 290 | 1.0054 | - | - | - | - | - | - | | 0.5059 | 300 | 1.1025 | - | - | - | - | - | - | | 0.5228 | 310 | 0.7316 | - | - | - | - | - | - | | 0.5396 | 320 | 1.648 | - | - | - | - | - | - | | 0.5565 | 330 | 1.0714 | - | - | - | - | - | - | | 0.5734 | 340 | 0.4809 | - | - | - | - | - | - | | 0.5902 | 350 | 0.3814 | - | - | - | - | - | - | | 0.6071 | 360 | 1.6564 | - | - | - | - | - | - | | 0.6239 | 370 | 1.0824 | - | - | - | - | - | - | | 0.6408 | 380 | 0.9652 | - | - | - | - | - | - | | 0.6577 | 390 | 1.2368 | - | - | - | - | - | - | | 0.6745 | 400 | 1.7904 | - | - | - | - | - | - | | 0.6914 | 410 | 0.8324 | - | - | - | - | - | - | | 0.7083 | 420 | 1.655 | - | - | - | - | - | - | | 0.7251 | 430 | 1.1056 | - | - | - | - | - | - | | 0.7420 | 440 | 1.6926 | - | - | - | - | - | - | | 0.7589 | 450 | 1.1129 | - | - | - | - | - | - | | 0.7757 | 460 | 1.3117 | - | - | - | - | - | - | | 0.7926 | 470 | 0.9942 | - | - | - | - | - | - | | 0.8094 | 480 | 1.0258 | - | - | - | - | - | - | | 0.8263 | 490 | 1.5217 | - | - | - | - | - | - | | 0.8432 | 500 | 0.8946 | - | - | - | - | - | - | | 0.8600 | 510 | 0.8951 | - | - | - | - | - | - | | 0.8769 | 520 | 0.5615 | - | - | - | - | - | - | | 0.8938 | 530 | 1.6551 | - | - | - | - | - | - | | 0.9106 | 540 | 0.2336 | - | - | - | - | - | - | | 0.9275 | 550 | 0.9635 | - | - | - | - | - | - | | 0.9444 | 560 | 0.6709 | - | - | - | - | - | - | | 0.9612 | 570 | 0.9109 | - | - | - | - | - | - | | 0.9781 | 580 | 1.7157 | - | - | - | - | - | - | | 0.9949 | 590 | 1.2344 | - | - | - | - | - | - | | 1.0 | 593 | - | 0.6764 | 0.6677 | 0.6679 | 0.6539 | 0.6370 | 0.6155 | | 1.0118 | 600 | 0.2666 | - | - | - | - | - | - | | 1.0287 | 610 | 0.8451 | - | - | - | - | - | - | | 1.0455 | 620 | 0.7215 | - | - | - | - | - | - | | 1.0624 | 630 | 0.3526 | - | - | - | - | - | - | | 1.0793 | 640 | 0.7853 | - | - | - | - | - | - | | 1.0961 | 650 | 0.8001 | - | - | - | - | - | - | | 1.1130 | 660 | 0.2595 | - | - | - | - | - | - | | 1.1298 | 670 | 0.4533 | - | - | - | - | - | - | | 1.1467 | 680 | 0.5806 | - | - | - | - | - | - | | 1.1636 | 690 | 0.4952 | - | - | - | - | - | - | | 1.1804 | 700 | 0.7964 | - | - | - | - | - | - | | 1.1973 | 710 | 0.7831 | - | - | - | - | - | - | | 1.2142 | 720 | 0.5613 | - | - | - | - | - | - | | 1.2310 | 730 | 0.6759 | - | - | - | - | - | - | | 1.2479 | 740 | 0.4816 | - | - | - | - | - | - | | 1.2648 | 750 | 0.5292 | - | - | - | - | - | - | | 1.2816 | 760 | 0.3936 | - | - | - | - | - | - | | 1.2985 | 770 | 0.7487 | - | - | - | - | - | - | | 1.3153 | 780 | 0.8308 | - | - | - | - | - | - | | 1.3322 | 790 | 0.3518 | - | - | - | - | - | - | | 1.3491 | 800 | 0.8495 | - | - | - | - | - | - | | 1.3659 | 810 | 1.0201 | - | - | - | - | - | - | | 1.3828 | 820 | 0.7711 | - | - | - | - | - | - | | 1.3997 | 830 | 0.6631 | - | - | - | - | - | - | | 1.4165 | 840 | 0.8094 | - | - | - | - | - | - | | 1.4334 | 850 | 0.5915 | - | - | - | - | - | - | | 1.4503 | 860 | 0.689 | - | - | - | - | - | - | | 1.4671 | 870 | 0.3538 | - | - | - | - | - | - | | 1.4840 | 880 | 0.4916 | - | - | - | - | - | - | | 1.5008 | 890 | 1.0626 | - | - | - | - | - | - | | 1.5177 | 900 | 0.7237 | - | - | - | - | - | - | | 1.5346 | 910 | 0.5194 | - | - | - | - | - | - | | 1.5514 | 920 | 0.682 | - | - | - | - | - | - | | 1.5683 | 930 | 0.452 | - | - | - | - | - | - | | 1.5852 | 940 | 0.8517 | - | - | - | - | - | - | | 1.6020 | 950 | 0.3138 | - | - | - | - | - | - | | 1.6189 | 960 | 1.0786 | - | - | - | - | - | - | | 1.6358 | 970 | 0.683 | - | - | - | - | - | - | | 1.6526 | 980 | 0.288 | - | - | - | - | - | - | | 1.6695 | 990 | 0.4779 | - | - | - | - | - | - | | 1.6863 | 1000 | 0.5353 | - | - | - | - | - | - | | 1.7032 | 1010 | 1.0529 | - | - | - | - | - | - | | 1.7201 | 1020 | 0.3482 | - | - | - | - | - | - | | 1.7369 | 1030 | 1.2722 | - | - | - | - | - | - | | 1.7538 | 1040 | 0.2862 | - | - | - | - | - | - | | 1.7707 | 1050 | 0.5556 | - | - | - | - | - | - | | 1.7875 | 1060 | 0.3363 | - | - | - | - | - | - | | 1.8044 | 1070 | 0.3817 | - | - | - | - | - | - | | 1.8212 | 1080 | 0.787 | - | - | - | - | - | - | | 1.8381 | 1090 | 0.8169 | - | - | - | - | - | - | | 1.8550 | 1100 | 0.8241 | - | - | - | - | - | - | | 1.8718 | 1110 | 0.8071 | - | - | - | - | - | - | | 1.8887 | 1120 | 0.7825 | - | - | - | - | - | - | | 1.9056 | 1130 | 0.6786 | - | - | - | - | - | - | | 1.9224 | 1140 | 0.2086 | - | - | - | - | - | - | | 1.9393 | 1150 | 0.8414 | - | - | - | - | - | - | | 1.9562 | 1160 | 0.7762 | - | - | - | - | - | - | | 1.9730 | 1170 | 0.5421 | - | - | - | - | - | - | | 1.9899 | 1180 | 0.2344 | - | - | - | - | - | - | | 2.0 | 1186 | - | 0.7265 | 0.7258 | 0.7167 | 0.7084 | 0.7002 | 0.6757 | | 2.0067 | 1190 | 0.1232 | - | - | - | - | - | - | | 2.0236 | 1200 | 0.473 | - | - | - | - | - | - | | 2.0405 | 1210 | 0.2913 | - | - | - | - | - | - | | 2.0573 | 1220 | 0.27 | - | - | - | - | - | - | | 2.0742 | 1230 | 0.33 | - | - | - | - | - | - | | 2.0911 | 1240 | 0.3323 | - | - | - | - | - | - | | 2.1079 | 1250 | 0.2355 | - | - | - | - | - | - | | 2.1248 | 1260 | 0.1089 | - | - | - | - | - | - | | 2.1417 | 1270 | 0.245 | - | - | - | - | - | - | | 2.1585 | 1280 | 0.4385 | - | - | - | - | - | - | | 2.1754 | 1290 | 0.3904 | - | - | - | - | - | - | | 2.1922 | 1300 | 0.4299 | - | - | - | - | - | - | | 2.2091 | 1310 | 0.1338 | - | - | - | - | - | - | | 2.2260 | 1320 | 0.2211 | - | - | - | - | - | - | | 2.2428 | 1330 | 0.2363 | - | - | - | - | - | - | | 2.2597 | 1340 | 0.0486 | - | - | - | - | - | - | | 2.2766 | 1350 | 0.1347 | - | - | - | - | - | - | | 2.2934 | 1360 | 0.1469 | - | - | - | - | - | - | | 2.3103 | 1370 | 0.064 | - | - | - | - | - | - | | 2.3272 | 1380 | 0.2582 | - | - | - | - | - | - | | 2.3440 | 1390 | 0.5994 | - | - | - | - | - | - | | 2.3609 | 1400 | 0.4847 | - | - | - | - | - | - | | 2.3777 | 1410 | 0.7184 | - | - | - | - | - | - | | 2.3946 | 1420 | 0.2852 | - | - | - | - | - | - | | 2.4115 | 1430 | 0.4838 | - | - | - | - | - | - | | 2.4283 | 1440 | 0.2932 | - | - | - | - | - | - | | 2.4452 | 1450 | 0.2452 | - | - | - | - | - | - | | 2.4621 | 1460 | 0.3531 | - | - | - | - | - | - | | 2.4789 | 1470 | 0.2666 | - | - | - | - | - | - | | 2.4958 | 1480 | 0.2835 | - | - | - | - | - | - | | 2.5126 | 1490 | 0.4196 | - | - | - | - | - | - | | 2.5295 | 1500 | 0.2563 | - | - | - | - | - | - | | 2.5464 | 1510 | 0.242 | - | - | - | - | - | - | | 2.5632 | 1520 | 0.4055 | - | - | - | - | - | - | | 2.5801 | 1530 | 0.489 | - | - | - | - | - | - | | 2.5970 | 1540 | 0.055 | - | - | - | - | - | - | | 2.6138 | 1550 | 0.6144 | - | - | - | - | - | - | | 2.6307 | 1560 | 0.9092 | - | - | - | - | - | - | | 2.6476 | 1570 | 0.6883 | - | - | - | - | - | - | | 2.6644 | 1580 | 0.4246 | - | - | - | - | - | - | | 2.6813 | 1590 | 0.317 | - | - | - | - | - | - | | 2.6981 | 1600 | 0.134 | - | - | - | - | - | - | | 2.7150 | 1610 | 0.2629 | - | - | - | - | - | - | | 2.7319 | 1620 | 0.3845 | - | - | - | - | - | - | | 2.7487 | 1630 | 0.4989 | - | - | - | - | - | - | | 2.7656 | 1640 | 0.5606 | - | - | - | - | - | - | | 2.7825 | 1650 | 0.0395 | - | - | - | - | - | - | | 2.7993 | 1660 | 0.2427 | - | - | - | - | - | - | | 2.8162 | 1670 | 0.1805 | - | - | - | - | - | - | | 2.8331 | 1680 | 0.1047 | - | - | - | - | - | - | | 2.8499 | 1690 | 0.717 | - | - | - | - | - | - | | 2.8668 | 1700 | 0.2244 | - | - | - | - | - | - | | 2.8836 | 1710 | 0.202 | - | - | - | - | - | - | | 2.9005 | 1720 | 0.2982 | - | - | - | - | - | - | | 2.9174 | 1730 | 0.1291 | - | - | - | - | - | - | | 2.9342 | 1740 | 0.3133 | - | - | - | - | - | - | | 2.9511 | 1750 | 0.1415 | - | - | - | - | - | - | | 2.9680 | 1760 | 0.2754 | - | - | - | - | - | - | | 2.9848 | 1770 | 0.5691 | - | - | - | - | - | - | | **3.0** | **1779** | **-** | **0.7298** | **0.7167** | **0.721** | **0.708** | **0.7126** | **0.692** | | 3.0017 | 1780 | 0.0698 | - | - | - | - | - | - | | 3.0185 | 1790 | 0.3206 | - | - | - | - | - | - | | 3.0354 | 1800 | 0.3665 | - | - | - | - | - | - | | 3.0523 | 1810 | 0.0085 | - | - | - | - | - | - | | 3.0691 | 1820 | 0.2066 | - | - | - | - | - | - | | 3.0860 | 1830 | 0.3554 | - | - | - | - | - | - | | 3.1029 | 1840 | 0.2967 | - | - | - | - | - | - | | 3.1197 | 1850 | 0.0984 | - | - | - | - | - | - | | 3.1366 | 1860 | 0.4303 | - | - | - | - | - | - | | 3.1535 | 1870 | 0.1165 | - | - | - | - | - | - | | 3.1703 | 1880 | 0.1966 | - | - | - | - | - | - | | 3.1872 | 1890 | 0.1865 | - | - | - | - | - | - | | 3.2040 | 1900 | 0.386 | - | - | - | - | - | - | | 3.2209 | 1910 | 0.1836 | - | - | - | - | - | - | | 3.2378 | 1920 | 0.2119 | - | - | - | - | - | - | | 3.2546 | 1930 | 0.0979 | - | - | - | - | - | - | | 3.2715 | 1940 | 0.286 | - | - | - | - | - | - | | 3.2884 | 1950 | 0.1315 | - | - | - | - | - | - | | 3.3052 | 1960 | 0.32 | - | - | - | - | - | - | | 3.3221 | 1970 | 0.5843 | - | - | - | - | - | - | | 3.3390 | 1980 | 0.201 | - | - | - | - | - | - | | 3.3558 | 1990 | 0.3161 | - | - | - | - | - | - | | 3.3727 | 2000 | 0.1855 | - | - | - | - | - | - | | 3.3895 | 2010 | 0.0993 | - | - | - | - | - | - | | 3.4064 | 2020 | 0.2922 | - | - | - | - | - | - | | 3.4233 | 2030 | 0.3549 | - | - | - | - | - | - | | 3.4401 | 2040 | 0.0385 | - | - | - | - | - | - | | 3.4570 | 2050 | 0.3567 | - | - | - | - | - | - | | 3.4739 | 2060 | 0.2036 | - | - | - | - | - | - | | 3.4907 | 2070 | 0.666 | - | - | - | - | - | - | | 3.5076 | 2080 | 0.127 | - | - | - | - | - | - | | 3.5245 | 2090 | 0.1066 | - | - | - | - | - | - | | 3.5413 | 2100 | 0.1094 | - | - | - | - | - | - | | 3.5582 | 2110 | 0.0989 | - | - | - | - | - | - | | 3.5750 | 2120 | 0.1002 | - | - | - | - | - | - | | 3.5919 | 2130 | 0.0959 | - | - | - | - | - | - | | 3.6088 | 2140 | 0.479 | - | - | - | - | - | - | | 3.6256 | 2150 | 0.2854 | - | - | - | - | - | - | | 3.6425 | 2160 | 0.3548 | - | - | - | - | - | - | | 3.6594 | 2170 | 0.2801 | - | - | - | - | - | - | | 3.6762 | 2180 | 0.2012 | - | - | - | - | - | - | | 3.6931 | 2190 | 0.3343 | - | - | - | - | - | - | | 3.7099 | 2200 | 0.4601 | - | - | - | - | - | - | | 3.7268 | 2210 | 0.1198 | - | - | - | - | - | - | | 3.7437 | 2220 | 0.152 | - | - | - | - | - | - | | 3.7605 | 2230 | 0.0899 | - | - | - | - | - | - | | 3.7774 | 2240 | 0.2245 | - | - | - | - | - | - | | 3.7943 | 2250 | 0.4322 | - | - | - | - | - | - | | 3.8111 | 2260 | 0.1466 | - | - | - | - | - | - | | 3.8280 | 2270 | 0.2181 | - | - | - | - | - | - | | 3.8449 | 2280 | 0.441 | - | - | - | - | - | - | | 3.8617 | 2290 | 0.4819 | - | - | - | - | - | - | | 3.8786 | 2300 | 0.3004 | - | - | - | - | - | - | | 3.8954 | 2310 | 0.1952 | - | - | - | - | - | - | | 3.9123 | 2320 | 0.2417 | - | - | - | - | - | - | | 3.9292 | 2330 | 0.4047 | - | - | - | - | - | - | | 3.9460 | 2340 | 0.2326 | - | - | - | - | - | - | | 3.9629 | 2350 | 0.1564 | - | - | - | - | - | - | | 3.9798 | 2360 | 0.1566 | - | - | - | - | - | - | | 3.9966 | 2370 | 0.1281 | - | - | - | - | - | - | | 4.0 | 2372 | - | 0.7326 | 0.7268 | 0.7245 | 0.7120 | 0.7055 | 0.7055 | * The bold row denotes the saved checkpoint.
### Framework Versions - Python: 3.11.11 - Sentence Transformers: 3.4.1 - Transformers: 4.47.1 - PyTorch: 2.5.1+cu124 - Accelerate: 1.2.1 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```