metadata

language:
  - pt
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:25863649
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: google o que causa urina turva
    sentences:
      - >-
        Um cagoule, cagoul, kagoule ou kagool (do francês cagoule significa
        balaclava) é o termo inglês britânico para um leve (geralmente sem
        forro), capa de chuva à prova de intempéries ou anorak com um capuz, que
        muitas vezes vem no joelho. O equivalente inglês canadense é
        quebra-vento ou K-Way".
      - >-
        Causas da Urina Nublada. 1 Infecção da bexiga (Cisite) A infecção da
        bexiga é uma infecção da bexiga, geralmente causada por bactérias ou,
        raramente, por Candida. 2 Desidratação é a perda excessiva de água
        corporal. 3 Gonorreia Em Mulheres Gonorreia é uma infecção bacteriana
        transmitida durante o contato sexual".
      - >-
        infecção vaginal ou desidratação. Se a urina é mais leitosa na
        aparência, isso pode ser devido à presença de bactérias, muco, gordura
        ou glóbulos vermelhos ou brancos. A propósito, a urina â-saudável deve
        ser amarela pálida ou de cor palha na aparência. Se a sua urina cheira.
        Engraçado. É mais provável devido a algo que você comeu".
  - source_sentence: como viver a vida sem depressão
    sentences:
      - >-
        a depressão resulta em uma perda da qualidade de vida. Por definição, um
        transtorno depressivo prejudica sua capacidade de funcionar
        adequadamente em seu trabalho, participar adequadamente de
        relacionamentos com os outros e de atender adequadamente às suas
        atividades de vida diária".
      - >-
        Mantém o controle de seus sentimentos e atividades. Quando você se sente
        mais deprimido, você pode começar a se afastar de atividades que você
        normalmente faz, como ir para a aula ou trabalhar, visitar amigos, fazer
        exercícios e até mesmo tomar banho. Você também pode começar a se sentir
        pior ou ter sintomas mais graves de depressão".
      - >-
        EUA Embaixadores e outras agências para sincronizar planos e executar
        atividades de informação e influenciar (IIA) em toda a gama de operações
        militares. 4o Grupo MIS (A) ".
  - source_sentence: o que faz tadasana significa
    sentences:
      - >-
        Esta é uma refeição vegetariana (VGML) que também é preparado chinês ou
        oriental-estilo. Vegetarian Lacto-Ovo Refeição (VLML) Esta é uma
        refeição vegetariana que também pode conter ovos e produtos lácteos.
        Contém um ou mais destes ingredientes: legumes, frutas frescas, ovos,
        produtos lácteos e leguminosas. Não contém qualquer tipo de peixe ou
        carne".
      - >-
        Tadasana, com 'tada' que significa 'montanha', é considerado como uma
        das posturas mais benéficas na ioga. Embora pareça ser bastante simples,
        uma pessoa tem que passar por muita prática para alcançar a postura
        perfeita de tadasana. Acredita-se que a asana também fornece benefícios
        físicos, mas mentais".
      - >-
        Alafia: Uma saudação, como olá com o significado de boa saúde ou paz
        (como shalom). Fanga: Uma dança de boas-vindas tradicional. Muitas vezes
        é escrito como funga.Ashe: (Pronuncia-se ah-shay) O Yoruba acredita que
        a cinza é uma força básica que emana do Criador que une todas as coisas
        vivas e não-viveres.lafia: Uma saudação, como olá com o significado de
        boa saúde ou paz (como shalom). Fanga: Uma dança de boas-vindas
        tradicional. Muitas vezes é escrito como funga".
  - source_sentence: qual é a coisa voando sobre a cidade esmeralda
    sentences:
      - >-
        " Maior aeroporto principal para Chincoteague, Virgínia: O principal
        aeroporto mais próximo de Chincoteague, Virginia é Salisbury-Ocean City
        Wicomico Regional Airport (SBY / KSBY). Este aeroporto fica em
        Salisbury, Maryland e fica a 47 milhas do centro de Chincoteague, VA. Se
        você está procurando voos domésticos para SBY, verifique as companhias
        aéreas que voam para SBY".
      - >-
        1 The Emerald City aparece no filme The Wizard of Oz (1939). 2 The
        Emerald City aparece em The Wizard of Oz série. 3 Depois que a Bruxa
        Malvada do Ocidente é ressuscitada por seus leais Macacos Voadores, ela
        lança um feitiço na Cidade Esmeralda que o mancha".
      - >-
        Isso dá a Esmeralda o valor adicional da boa sorte, da providência e
        como uma ponte entre a mente humana e os escritos Divinos. Onde quer que
        haja alguém impactando a mente e o espírito da humanidade de maneiras
        profundas, é provável que você encontre a Esmeralda na imagem. Esmeralda
        vem sob o domínio da deusa Vênus".
  - source_sentence: o que ajuda a síndrome de ibs
    sentences:
      - >-
        óleo de hortelã-revestida com antecérico é amplamente utilizado para a
        síndrome do intestino irritável. Tem a intenção de reduzir a dor
        abdominal e inchaço da síndrome do intestino irritável. Peppermint é
        considerada uma erva carminativa, o que significa que é usado para
        eliminar o excesso de gás nos intestinos. Embora novas pesquisas sejam
        necessárias, estudos preliminares indicam que pode aliviar os sintomas
        da SII".
      - diarreia ou prisão de ventre que não responde ao tratamento domiciliar".
      - >-
        Este tipo de halva é feito por fritar farinha (como sêmola) em óleo,
        misturando-o em um roux, e depois cozinhá-lo com um xarope açucarado.
        Esta variedade é popular na Grécia, Azerbaijão, Irã, Turquia, Somália,
        índia, Paquistão e Afeganistão".
datasets:
  - cnmoro/AllTripletsMsMarco-PTBR
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: SentenceTransformer
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: cosine_accuracy@1
            value: 0.16
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.34
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.38
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.16
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08800000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.056000000000000015
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07233333333333332
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.12233333333333335
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.169
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.21633333333333332
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.17347962524637853
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.22666666666666668
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.13734138567741627
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: cosine_accuracy@1
            value: 0.48
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.82
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.86
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.48
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.43999999999999995
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.408
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.35999999999999993
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.035316726913150166
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.10434144077897482
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.15231964640086332
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.2237637244339288
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4246552618150319
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6176666666666667
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.31123449548810894
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: cosine_accuracy@1
            value: 0.32
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.58
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.72
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.82
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.32
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15200000000000002
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08799999999999997
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.2866666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5466666666666667
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6933333333333332
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.79
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.541603756700773
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4797777777777777
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4632721572721572
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: cosine_accuracy@1
            value: 0.16
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.32
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.38
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.16
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.052000000000000005
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.047079365079365075
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.12374603174603176
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.1498015873015873
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.19921428571428573
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.14911410247271004
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2208571428571429
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.10914868671112705
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: cosine_accuracy@1
            value: 0.5
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.68
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.76
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.86
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.5
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19599999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.122
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.25
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.44
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.49
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.61
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5140251570207169
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6078333333333333
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4296608736936407
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: cosine_accuracy@1
            value: 0.08
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.32
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.46
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.58
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.10666666666666665
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05800000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.32
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.46
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.58
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.31757857296738545
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2347460317460317
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.24643617899193362
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: cosine_accuracy@1
            value: 0.26
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.46
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.48
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.26
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.22666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.2
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.14800000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.039136679314288055
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.07088473736441431
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.08854886067737688
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.09738297754672119
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.20662886108023884
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.33716666666666667
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.08492712298780619
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: cosine_accuracy@1
            value: 0.06
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.12
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.18
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.3
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.06
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.039999999999999994
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.036000000000000004
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.030000000000000006
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.06
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.11
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.17
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.27
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.14834320225800574
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.11593650793650795
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12214508911612589
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: cosine_accuracy@1
            value: 0.7
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.84
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.94
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.30666666666666664
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.21199999999999997
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.11399999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.644
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7613333333333333
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.848
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.902
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.796606045632188
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7831666666666668
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7555666834462891
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: cosine_accuracy@1
            value: 0.18
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.38
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.48
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.58
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.16666666666666663
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09000000000000002
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.03866666666666667
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.10466666666666667
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.1456666666666667
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.18566666666666667
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.1754827925505982
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2969126984126984
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12469236976328293
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: cosine_accuracy@1
            value: 0.08
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.28
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.36
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.54
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05400000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.28
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.36
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.54
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2899394224946307
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.21268253968253967
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.22184431538753369
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: cosine_accuracy@1
            value: 0.34
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.44
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.46
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.52
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.34
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.096
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05600000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.34
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.43
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.44
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.495
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4215626178273768
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3998571428571428
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4072112112025905
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: cosine_accuracy@1
            value: 0.30612244897959184
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4897959183673469
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6122448979591837
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7959183673469388
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.30612244897959184
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2857142857142857
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.28571428571428575
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.2714285714285714
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.017318112827283315
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.04934081962696573
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.08015471400681852
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.1539608360137575
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.28125127808062544
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4444930353093618
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.1901047659008045
            name: Cosine Map@100
      - task:
          type: nano-beir
          name: Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: cosine_accuracy@1
            value: 0.2789324960753532
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4438304552590267
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5286342229199373
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6181475667189953
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.2789324960753532
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1927472527472527
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15767032967032968
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.11534065934065933
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.15311673467698103
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2664086945781836
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3266788314143574
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.40487090951605337
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3415592843189738
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3829048366599387
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.27719887197221665
            name: Cosine Map@100

SentenceTransformer

This is a sentence-transformers model trained on the all_triplets_ms_marco-ptbr dataset. It maps sentences & paragraphs to a 512-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
Maximum Sequence Length: inf tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- all_triplets_ms_marco-ptbr
Language: pt

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): StaticEmbedding(
    (embedding): EmbeddingBag(29794, 512, mode='mean')
  )
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("cnmoro/static-retrieval-distilbert-ptbr")
# Run inference
sentences = [
    'o que ajuda a síndrome de ibs',
    'óleo de hortelã-revestida com antecérico é amplamente utilizado para a síndrome do intestino irritável. Tem a intenção de reduzir a dor abdominal e inchaço da síndrome do intestino irritável. Peppermint é considerada uma erva carminativa, o que significa que é usado para eliminar o excesso de gás nos intestinos. Embora novas pesquisas sejam necessárias, estudos preliminares indicam que pode aliviar os sintomas da SII".',
    'diarreia ou prisão de ventre que não responde ao tratamento domiciliar".',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Datasets: NanoClimateFEVER, NanoDBPedia, NanoFEVER, NanoFiQA2018, NanoHotpotQA, NanoMSMARCO, NanoNFCorpus, NanoNQ, NanoQuoraRetrieval, NanoSCIDOCS, NanoArguAna, NanoSciFact and NanoTouche2020
Evaluated with InformationRetrievalEvaluator

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
cosine_accuracy@1	0.16	0.48	0.32	0.16	0.5	0.08	0.26	0.06	0.7	0.18	0.08	0.34	0.3061
cosine_accuracy@3	0.26	0.7	0.58	0.26	0.68	0.32	0.42	0.12	0.84	0.38	0.28	0.44	0.4898
cosine_accuracy@5	0.34	0.82	0.72	0.32	0.76	0.46	0.46	0.18	0.9	0.48	0.36	0.46	0.6122
cosine_accuracy@10	0.38	0.86	0.82	0.38	0.86	0.58	0.48	0.3	0.94	0.58	0.54	0.52	0.7959
cosine_precision@1	0.16	0.48	0.32	0.16	0.5	0.08	0.26	0.06	0.7	0.18	0.08	0.34	0.3061
cosine_precision@3	0.1	0.44	0.2	0.0933	0.2933	0.1067	0.2267	0.04	0.3067	0.1667	0.0933	0.1533	0.2857
cosine_precision@5	0.088	0.408	0.152	0.072	0.196	0.092	0.2	0.036	0.212	0.14	0.072	0.096	0.2857
cosine_precision@10	0.056	0.36	0.088	0.052	0.122	0.058	0.148	0.03	0.114	0.09	0.054	0.056	0.2714
cosine_recall@1	0.0723	0.0353	0.2867	0.0471	0.25	0.08	0.0391	0.06	0.644	0.0387	0.08	0.34	0.0173
cosine_recall@3	0.1223	0.1043	0.5467	0.1237	0.44	0.32	0.0709	0.11	0.7613	0.1047	0.28	0.43	0.0493
cosine_recall@5	0.169	0.1523	0.6933	0.1498	0.49	0.46	0.0885	0.17	0.848	0.1457	0.36	0.44	0.0802
cosine_recall@10	0.2163	0.2238	0.79	0.1992	0.61	0.58	0.0974	0.27	0.902	0.1857	0.54	0.495	0.154
cosine_ndcg@10	0.1735	0.4247	0.5416	0.1491	0.514	0.3176	0.2066	0.1483	0.7966	0.1755	0.2899	0.4216	0.2813
cosine_mrr@10	0.2267	0.6177	0.4798	0.2209	0.6078	0.2347	0.3372	0.1159	0.7832	0.2969	0.2127	0.3999	0.4445
cosine_map@100	0.1373	0.3112	0.4633	0.1091	0.4297	0.2464	0.0849	0.1221	0.7556	0.1247	0.2218	0.4072	0.1901

Nano BEIR

Dataset: NanoBEIR_mean
Evaluated with NanoBEIREvaluator

Metric	Value
cosine_accuracy@1	0.2789
cosine_accuracy@3	0.4438
cosine_accuracy@5	0.5286
cosine_accuracy@10	0.6181
cosine_precision@1	0.2789
cosine_precision@3	0.1927
cosine_precision@5	0.1577
cosine_precision@10	0.1153
cosine_recall@1	0.1531
cosine_recall@3	0.2664
cosine_recall@5	0.3267
cosine_recall@10	0.4049
cosine_ndcg@10	0.3416
cosine_mrr@10	0.3829
cosine_map@100	0.2772

Training Details

Training Dataset

all_triplets_ms_marco-ptbr

Dataset: all_triplets_ms_marco-ptbr at f934503
Size: 25,863,649 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 5 characters mean: 35.31 characters max: 105 characters	min: 31 characters mean: 356.8 characters max: 1050 characters	min: 13 characters mean: 359.92 characters max: 1153 characters

Samples:

anchor	positive	negative
`partes mais quentes da califórnia em dezembro`	`as melhores praias da Califórnia para o clima quente do inverno estão ao longo da costa sul, particularmente as margens viradas para o sul. As temperaturas mais quentes acontecem em Avila Beach, Long Beach e Laguna Beach, onde os dias se dem até pelo menos 67 graus F (19 C) em média em dezembro e janeiro".`	`Outros destinos da ilha do Caribe com uma combinação de clima quente e não muita chuva em dezembro incluem Kingston, Jamaica (87 F), St. Kitts (85 F) e Nassau, Bahamas (79 F). Nos EUA continentais, o clima de férias mais quente em dezembro é mais frequentemente a Flórida. Tente afundar seus dedos na areia branca quente e macia de Nápoles e Sarasota, dois dos nossos locais de férias de inverno românticos da Flórida da Costa do Golfo da Flórida".`
`definição de anosmia`	`Anosmia (/aen-É-zmiÉ/) A sÉ-zmiÉ é a incapacidade de perceber o odor ou a falta de funcionamento da autaraction a perda do sentido.`	`Anemia é um termo médico que se refere a um número reduzido de glóbulos vermelhos circulantes (RBC), hemoglobina (Hb), ou ambos. Não é uma doença específica, mas sim o resultado de algum outro processo de doença ou condição.nemia é um termo médico referindo-se a um número reduzido de glóbulos vermelhos circulantes (RBC), hemoglobina (Hb), ou ambos. Não é uma doença específica, mas sim o resultado de algum outro processo ou condição de doença".`
`can fêmeas obter hemofilia`	uma fêmea que herda um afetado x cromossomo torna-se um portador de hemofilia que ela pode passar o gene afetado para seus filhos, além de uma mulher que é um portador às vezes pode ter sintomas de hemofilia na verdade alguns médicos descrevem essas mulheres como tendo mulheres leves que carregam o gene da hemofilia que carregam o gene da hemofilia e têm quaisquer sintomas do transtorno deve ser verificado e cuidado por um provedor de saúde de boa qualidade cuidados médicos e enfermeiros que podem evitar que os problemas sérios que saibam que muitos.	Hemofilia é um X ligado ou sexo ligado a doença hereditária que significa que o defeito é realizado no cromossomo X. As fêmeas têm dois cromossomos X e os machos têm um cromossomo X e um cromossomo Y. O cromossomo X, que carrega o gene da hemofilia em homens, faz com que Fator VIII ou Fator IX esteja ausente ou deficiente (nível baixo). Cada criança de um portador de hemofilia tem 50% de chance de ser afetada pela hemofilia; seja ter hemofilia para um macho ou ser portadora de uma mulher".

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        512,
        384,
        256,
        128,
        64,
        32,
        16,
        8
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

all_triplets_ms_marco-ptbr

Dataset: all_triplets_ms_marco-ptbr at f934503
Size: 527,832 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 characters mean: 36.15 characters max: 193 characters	min: 20 characters mean: 360.3 characters max: 1097 characters	min: 14 characters mean: 365.67 characters max: 1145 characters

Samples:

anchor	positive	negative
`diferença entre o ovo cozido duro e o ovo escalfado`	`o ovo é escalfado (ou cozido) quando o branco é cozido e a gema ainda é escorrendo, um ovo cozido duro é cozido em sua casca por 7 a 8 minutos até que seja cozido sólido todo o caminho. Carmen D 4 anos atrás. Os polegares para cima. 0".`	`mexidos, escalfados, fritos ou cozidos, e dado todas essas variações, a questão de longa duração que eles podem ser armazenados com segurança é uma boa a considerar. Uma bactéria chamada Salmonella enteritidis pode estar presente dentro da gema, mas ovos duros os torna seguros para comer".`
`quando você pode coletar segurança social se deficientes`	`Como a Segurança Social pagará benefícios de invalidez a uma pessoa com deficiência é determinada pela data em que você apresentou sua reivindicação de deficiência ao se candidatar à segurança social e/ou incapacidade da SSI.`	Se for esse o caso, você não terá mais direito a benefícios de Deficiência da Segurança Social, mas você pode ter direito a benefícios de aposentadoria da Previdência Social uma vez que você atinja a idade de 65 anos. Se você decidir voltar ao trabalho seus benefícios não vai parar imediatamente. Você pode ganhar renda em uma base de â-trialâ para até nove meses antes de seus benefícios de Deficiência Social são revogados. Se você tentar voltar ao trabalho e descobrir que você é incapaz de lidar com isso, seus Benefícios de Segurança Social não terminará.ou pode ganhar renda em uma base de âtrialâ por até nove meses antes de seus benefícios de deficientes de segurança social são revogados. Se você tentar voltar ao trabalho e descobrir que não consegue lidar com isso, seus Benefícios de Segurança Social não terminarão".
`número de contato da sede da união ocidental`	`número de telefone da União Ocidental. O número e as etapas abaixo são votados no 1 de 4 por mais de 7190 clientes da Western Union. 800-999-9660. Suporte telefônico da Western Union. Leia as principais etapas e dicas abaixo. Eles chamam você em vez dissoNão esperando em espera. Free.ress 1 e continue pressionando 0. Este número de telefone é popular entre outros clientes da Western Union, mas não se esqueça de seguir os 6 passos mais abaixo".`	`Neste artigo eu listei o número de telefone de serviço ao cliente Western Union essencial e o número de telefone de contato e números gratuitos para a Western Union. Western Union operando em muitos países, então eu listei números de telefone de atendimento ao cliente internacional Western Union. Se você é o cliente da Western Union e gosta de saber informações sobre produtos e serviços da Western Union, basta usar os seguintes números".`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        512,
        384,
        256,
        128,
        64,
        32,
        16,
        8
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
learning_rate: 0.2
num_train_epochs: 5
warmup_ratio: 0.1
bf16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
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: 0.2
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 5
max_steps: -1
lr_scheduler_type: linear
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
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: False
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
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: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	NanoClimateFEVER_cosine_ndcg@10	NanoDBPedia_cosine_ndcg@10	NanoFEVER_cosine_ndcg@10	NanoFiQA2018_cosine_ndcg@10	NanoHotpotQA_cosine_ndcg@10	NanoMSMARCO_cosine_ndcg@10	NanoNFCorpus_cosine_ndcg@10	NanoNQ_cosine_ndcg@10	NanoQuoraRetrieval_cosine_ndcg@10	NanoSCIDOCS_cosine_ndcg@10	NanoArguAna_cosine_ndcg@10	NanoSciFact_cosine_ndcg@10	NanoTouche2020_cosine_ndcg@10	NanoBEIR_mean_cosine_ndcg@10
0.0000	1	66.3307	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0198	1000	42.3936	27.4352	0.1314	0.3901	0.4362	0.0856	0.4261	0.2743	0.1524	0.1226	0.7497	0.1547	0.1544	0.4066	0.2984	0.2910
0.0396	2000	21.4189	17.5353	0.1443	0.4301	0.5087	0.1281	0.4315	0.2600	0.1859	0.1462	0.7842	0.1978	0.1944	0.4489	0.3432	0.3233
0.0594	3000	15.8675	14.6976	0.1579	0.4524	0.5459	0.1350	0.4307	0.2972	0.1980	0.1443	0.7807	0.1921	0.2016	0.4302	0.3561	0.3325
0.0792	4000	14.0655	13.5888	0.1803	0.4522	0.5321	0.1402	0.4479	0.2982	0.1914	0.1912	0.7992	0.2001	0.2143	0.4502	0.3432	0.3416
0.0990	5000	13.2932	13.0002	0.1926	0.4523	0.5118	0.1607	0.4451	0.3059	0.2048	0.2168	0.7903	0.1974	0.2387	0.4653	0.3520	0.3487
0.1188	6000	12.8258	12.6530	0.1998	0.4510	0.5437	0.1296	0.4506	0.3335	0.2100	0.1894	0.8074	0.1761	0.2423	0.4456	0.3688	0.3498
0.1386	7000	12.5101	12.3932	0.1775	0.4638	0.4978	0.1503	0.4547	0.3197	0.2037	0.1864	0.8178	0.1757	0.1987	0.4518	0.3382	0.3412
0.1584	8000	12.2601	12.1873	0.1884	0.4794	0.5263	0.1668	0.4764	0.3603	0.2115	0.1673	0.7835	0.1720	0.2266	0.4534	0.3535	0.3512
0.1782	9000	12.0884	12.0142	0.2139	0.4735	0.5170	0.1598	0.4498	0.3448	0.2002	0.1983	0.7901	0.1651	0.2351	0.4458	0.3240	0.3475
0.1980	10000	11.9352	11.8797	0.2123	0.4813	0.5146	0.1452	0.5095	0.3642	0.1983	0.1637	0.8041	0.1699	0.2384	0.4545	0.3198	0.3520
0.2178	11000	11.8034	11.7615	0.1776	0.4579	0.5237	0.1673	0.4808	0.3068	0.2009	0.1828	0.8173	0.1706	0.2572	0.4408	0.3205	0.3465
0.2376	12000	11.6906	11.6589	0.1789	0.4593	0.5512	0.1341	0.4894	0.3340	0.2106	0.1811	0.8192	0.1773	0.2381	0.4480	0.3209	0.3494
0.2573	13000	11.5868	11.5586	0.1877	0.4648	0.5137	0.1494	0.4939	0.3212	0.2193	0.2025	0.8120	0.1640	0.2452	0.4258	0.3561	0.3504
0.2771	14000	11.4752	11.4752	0.1938	0.4411	0.5186	0.1418	0.4839	0.3411	0.2106	0.1688	0.8217	0.1744	0.2768	0.4688	0.3384	0.3523
0.2969	15000	11.4299	11.3873	0.1989	0.4501	0.5109	0.1309	0.5037	0.3280	0.2040	0.1649	0.8035	0.1707	0.2549	0.4714	0.3308	0.3479
0.3167	16000	11.3369	11.3173	0.1880	0.4666	0.4988	0.1430	0.5086	0.3385	0.2054	0.1786	0.8181	0.1712	0.2766	0.4555	0.3220	0.3516
0.3365	17000	11.2737	11.2503	0.1748	0.4673	0.4849	0.1485	0.4902	0.3567	0.2160	0.1501	0.8059	0.1659	0.2476	0.4728	0.3121	0.3456
0.3563	18000	11.2138	11.1802	0.1738	0.4619	0.5408	0.1426	0.4986	0.3427	0.2193	0.1594	0.7995	0.1597	0.2567	0.4331	0.3140	0.3463
0.3761	19000	11.1662	11.1250	0.1625	0.4522	0.5313	0.1419	0.5093	0.3499	0.1982	0.1713	0.8000	0.1693	0.2332	0.4799	0.3353	0.3488
0.3959	20000	11.0674	11.0633	0.1627	0.4608	0.5167	0.1368	0.5025	0.3653	0.2090	0.1743	0.8166	0.1670	0.2281	0.4614	0.3408	0.3494
0.4157	21000	11.0251	11.0233	0.1730	0.4695	0.4854	0.1417	0.5211	0.3393	0.2246	0.1477	0.8146	0.1692	0.2148	0.4584	0.3356	0.3458
0.4355	22000	10.9932	10.9695	0.1709	0.4630	0.5161	0.1400	0.4945	0.3507	0.2226	0.1585	0.8103	0.1595	0.2355	0.4325	0.3343	0.3453
0.4553	23000	10.9327	10.9186	0.1803	0.4509	0.5341	0.1454	0.5241	0.3485	0.2032	0.1480	0.8056	0.1634	0.2206	0.4557	0.3266	0.3466
0.4751	24000	10.8936	10.8830	0.1891	0.4450	0.5202	0.1485	0.5006	0.3427	0.2079	0.1639	0.8115	0.1731	0.2213	0.4269	0.3424	0.3456
0.4949	25000	10.8654	10.8392	0.1610	0.4479	0.5524	0.1547	0.5002	0.3377	0.2128	0.1802	0.7996	0.1937	0.2240	0.4506	0.3097	0.3480
0.5147	26000	10.8168	10.7826	0.1784	0.4558	0.5211	0.1482	0.5099	0.3531	0.2165	0.1456	0.8090	0.1782	0.2367	0.4240	0.3251	0.3463
0.5345	27000	10.7554	10.7164	0.1841	0.4593	0.5183	0.1377	0.4843	0.3469	0.2066	0.1632	0.8099	0.1818	0.2779	0.4305	0.3270	0.3483
0.5543	28000	10.6605	10.6510	0.1780	0.4566	0.5328	0.1439	0.4923	0.3519	0.2152	0.1507	0.8060	0.1838	0.2585	0.4256	0.3147	0.3469
0.5741	29000	10.6202	10.5959	0.1866	0.4668	0.5370	0.1553	0.5118	0.3699	0.2265	0.1553	0.8090	0.1732	0.2614	0.4287	0.3193	0.3539
0.5939	30000	10.5399	10.5401	0.1862	0.4593	0.5237	0.1510	0.5273	0.3353	0.2101	0.1594	0.8092	0.1709	0.2643	0.4308	0.3199	0.3498
0.6137	31000	10.5212	10.4866	0.2000	0.4547	0.5131	0.1450	0.5213	0.3341	0.2136	0.1518	0.8094	0.1726	0.2911	0.4246	0.3388	0.3516
0.6335	32000	10.4767	10.4375	0.1873	0.4487	0.5162	0.1377	0.5186	0.3463	0.2184	0.1711	0.8087	0.1769	0.2871	0.4441	0.3297	0.3531
0.6533	33000	10.4247	10.4089	0.1949	0.4572	0.5322	0.1524	0.5286	0.3309	0.2204	0.1464	0.8006	0.1765	0.2727	0.4314	0.3323	0.3520
0.6731	34000	10.389	10.3680	0.1867	0.4628	0.5265	0.1369	0.5196	0.3411	0.2224	0.1597	0.8003	0.1702	0.2678	0.4386	0.3163	0.3499
0.6929	35000	10.3299	10.3354	0.1937	0.4614	0.5042	0.1430	0.5215	0.3416	0.2159	0.1488	0.8101	0.1764	0.2601	0.4525	0.3192	0.3499
0.7127	36000	10.3103	10.3054	0.1764	0.4555	0.5281	0.1577	0.5291	0.3338	0.2049	0.1483	0.7980	0.1660	0.2626	0.4153	0.3137	0.3453
0.7325	37000	10.2869	10.2670	0.1703	0.4488	0.5188	0.1560	0.5200	0.3370	0.2118	0.1513	0.8108	0.1671	0.2853	0.4057	0.3102	0.3456
0.7523	38000	10.2414	10.2453	0.1713	0.4556	0.5400	0.1568	0.5228	0.3359	0.2081	0.1624	0.8063	0.1636	0.2644	0.4413	0.3117	0.3492
0.7720	39000	10.231	10.2169	0.1595	0.4577	0.5599	0.1510	0.5195	0.3300	0.2070	0.1635	0.8145	0.1615	0.2846	0.4269	0.3236	0.3507
0.7918	40000	10.2115	10.1964	0.1734	0.4621	0.5414	0.1481	0.5300	0.3438	0.2072	0.1712	0.8062	0.1639	0.2815	0.4122	0.3000	0.3493
0.8116	41000	10.1947	10.1671	0.1712	0.4559	0.5450	0.1523	0.5145	0.3392	0.2198	0.1588	0.7927	0.1734	0.2826	0.4281	0.3014	0.3488
0.8314	42000	10.1666	10.1581	0.1648	0.4464	0.5555	0.1639	0.5014	0.3477	0.2099	0.1443	0.7988	0.1640	0.2784	0.4482	0.2983	0.3478
0.8512	43000	10.1528	10.1265	0.1789	0.4437	0.5328	0.1525	0.5266	0.3369	0.2016	0.1561	0.8097	0.1742	0.2863	0.4503	0.3008	0.3500
0.8710	44000	10.1054	10.1122	0.1716	0.4542	0.5310	0.1610	0.5359	0.3454	0.2022	0.1725	0.7948	0.1666	0.2840	0.4246	0.3149	0.3507
0.8908	45000	10.0878	10.0890	0.1729	0.4489	0.5533	0.1561	0.5401	0.3413	0.2135	0.1510	0.7989	0.1735	0.2950	0.4348	0.3202	0.3538
0.9106	46000	10.0875	10.0730	0.1776	0.4550	0.5499	0.1563	0.5313	0.3357	0.2084	0.1578	0.8058	0.1739	0.2976	0.4468	0.3176	0.3549
0.9304	47000	10.0615	10.0561	0.1816	0.4569	0.5310	0.1583	0.5279	0.3332	0.2058	0.1532	0.7976	0.1727	0.2813	0.4513	0.3146	0.3512
0.9502	48000	10.0378	10.0374	0.1916	0.4558	0.5242	0.1552	0.5368	0.3518	0.2050	0.1617	0.8065	0.1736	0.2898	0.4268	0.3109	0.3531
0.9700	49000	10.0393	10.0283	0.1809	0.4542	0.5319	0.1594	0.5240	0.3329	0.2070	0.1595	0.7998	0.1670	0.2885	0.4522	0.3204	0.3521
0.9898	50000	10.0035	10.0112	0.1721	0.4495	0.5200	0.1548	0.5294	0.3514	0.2124	0.1597	0.8063	0.1798	0.2785	0.4479	0.3322	0.3534
1.0096	51000	9.9575	10.0040	0.1737	0.4476	0.5422	0.1527	0.5345	0.3513	0.2076	0.1513	0.8071	0.1681	0.2715	0.4547	0.3149	0.3521
1.0294	52000	9.9083	9.9996	0.1668	0.4530	0.5315	0.1645	0.5212	0.3375	0.2168	0.1458	0.8046	0.1720	0.2746	0.4432	0.3234	0.3504
1.0492	53000	9.9229	9.9895	0.1777	0.4434	0.5348	0.1601	0.5158	0.3390	0.2130	0.1461	0.8014	0.1717	0.2808	0.4546	0.3161	0.3504
1.0690	54000	9.884	9.9758	0.1797	0.4507	0.5372	0.1685	0.5202	0.3398	0.2174	0.1739	0.7949	0.1744	0.2944	0.4334	0.3191	0.3541
1.0888	55000	9.9108	9.9650	0.1780	0.4458	0.5249	0.1510	0.5190	0.3492	0.2222	0.1639	0.7968	0.1895	0.2878	0.4251	0.3153	0.3514
1.1086	56000	9.9019	9.9556	0.1893	0.4465	0.5368	0.1514	0.5131	0.3384	0.2151	0.1609	0.8029	0.1886	0.2993	0.4280	0.3223	0.3533
1.1284	57000	9.8931	9.9392	0.1837	0.4409	0.5381	0.1632	0.5254	0.3332	0.2046	0.1470	0.8067	0.1915	0.2797	0.4167	0.3212	0.3501
1.1482	58000	9.8714	9.9229	0.1731	0.4440	0.5289	0.1477	0.5073	0.3257	0.2063	0.1631	0.8079	0.1844	0.3001	0.4391	0.3194	0.3498
1.1680	59000	9.885	9.9159	0.1756	0.4498	0.5274	0.1580	0.5156	0.3227	0.2101	0.1470	0.8042	0.1783	0.3026	0.4215	0.3237	0.3490
1.1878	60000	9.8824	9.9016	0.1794	0.4512	0.5261	0.1523	0.5093	0.3427	0.1964	0.1468	0.8029	0.1756	0.2898	0.4325	0.3173	0.3479
1.2076	61000	9.8846	9.8969	0.1768	0.4518	0.5452	0.1643	0.5087	0.3471	0.2004	0.1509	0.7959	0.1847	0.2954	0.4386	0.3099	0.3515
1.2274	62000	9.8534	9.8831	0.1848	0.4532	0.5422	0.1583	0.5177	0.3546	0.2087	0.1546	0.7985	0.1815	0.3024	0.4335	0.3285	0.3553
1.2472	63000	9.8494	9.8759	0.1776	0.4490	0.5305	0.1641	0.5138	0.3517	0.2043	0.1474	0.8040	0.1809	0.2947	0.4252	0.3183	0.3509
1.2670	64000	9.8514	9.8639	0.1820	0.4553	0.5386	0.1569	0.5055	0.3442	0.2116	0.1396	0.7949	0.1807	0.2820	0.4225	0.3154	0.3484
1.2867	65000	9.8341	9.8563	0.1772	0.4507	0.5300	0.1579	0.5072	0.3392	0.2067	0.1529	0.7961	0.1825	0.2874	0.4215	0.3195	0.3484
1.3065	66000	9.8417	9.8492	0.1784	0.4557	0.5251	0.1598	0.5011	0.3324	0.2183	0.1566	0.7928	0.1821	0.2873	0.4181	0.3153	0.3479
1.3263	67000	9.8081	9.8369	0.1831	0.4488	0.5360	0.1681	0.5046	0.3317	0.2064	0.1467	0.8013	0.1738	0.2887	0.4381	0.3043	0.3486
1.3461	68000	9.8001	9.8274	0.1842	0.4563	0.5387	0.1647	0.5080	0.3174	0.2089	0.1595	0.7964	0.1705	0.2918	0.4187	0.3054	0.3477
1.3659	69000	9.8059	9.8159	0.1827	0.4570	0.5528	0.1715	0.5207	0.3289	0.2046	0.1543	0.8094	0.1757	0.2839	0.4281	0.3025	0.3517
1.3857	70000	9.7848	9.8117	0.1656	0.4547	0.5381	0.1562	0.5091	0.3233	0.2127	0.1539	0.8000	0.1722	0.2885	0.4168	0.3091	0.3462
1.4055	71000	9.7847	9.8049	0.1786	0.4499	0.5495	0.1675	0.5194	0.3180	0.2133	0.1587	0.8025	0.1588	0.2895	0.4224	0.3056	0.3487
1.4253	72000	9.7587	9.7976	0.1706	0.4562	0.5425	0.1530	0.5283	0.3356	0.2125	0.1564	0.8055	0.1660	0.2939	0.4219	0.3005	0.3495
1.4451	73000	9.7652	9.7898	0.1787	0.4479	0.5406	0.1539	0.5281	0.3291	0.2088	0.1438	0.8058	0.1767	0.2938	0.4115	0.2960	0.3473
1.4649	74000	9.7507	9.7830	0.1746	0.4394	0.5426	0.1647	0.5201	0.3290	0.2131	0.1507	0.8039	0.1643	0.2856	0.4510	0.3030	0.3494
1.4847	75000	9.7412	9.7757	0.1701	0.4386	0.5244	0.1639	0.5140	0.3218	0.2111	0.1542	0.8086	0.1714	0.2765	0.4224	0.2973	0.3442
1.5045	76000	9.7412	9.7727	0.1823	0.4477	0.5337	0.1544	0.5117	0.3381	0.2074	0.1605	0.8079	0.1710	0.2820	0.4325	0.2996	0.3484
1.5243	77000	9.7475	9.7626	0.1743	0.4423	0.5343	0.1511	0.5142	0.3224	0.2124	0.1567	0.8076	0.1802	0.2946	0.4303	0.3044	0.3481
1.5441	78000	9.7512	9.7590	0.1737	0.4406	0.5323	0.1535	0.5102	0.3419	0.2099	0.1476	0.8058	0.1626	0.2877	0.4073	0.3015	0.3442
1.5639	79000	9.7406	9.7501	0.1735	0.4472	0.5189	0.1639	0.5148	0.3232	0.2065	0.1555	0.8015	0.1698	0.2826	0.4320	0.3047	0.3457
1.5837	80000	9.7409	9.7426	0.1799	0.4405	0.5225	0.1627	0.5158	0.3487	0.2051	0.1608	0.8079	0.1657	0.2857	0.4469	0.3014	0.3495
1.6035	81000	9.7125	9.7399	0.1781	0.4402	0.5230	0.1564	0.5153	0.3439	0.2167	0.1622	0.8070	0.1706	0.3040	0.4512	0.3071	0.3520
1.6233	82000	9.7164	9.7319	0.1806	0.4485	0.5317	0.1486	0.5220	0.3353	0.2087	0.1604	0.8033	0.1783	0.2899	0.4178	0.3025	0.3483
1.6431	83000	9.7203	9.7257	0.1766	0.4513	0.5120	0.1581	0.5108	0.3375	0.2084	0.1635	0.8085	0.1682	0.2904	0.4334	0.2932	0.3471
1.6629	84000	9.7035	9.7229	0.1759	0.4447	0.5391	0.1555	0.5104	0.3369	0.2067	0.1584	0.8036	0.1754	0.2943	0.4266	0.3032	0.3485
1.6827	85000	9.7277	9.7206	0.1757	0.4401	0.5229	0.1540	0.5188	0.3448	0.2070	0.1521	0.8078	0.1731	0.2967	0.4287	0.2984	0.3477
1.7025	86000	9.6992	9.7184	0.1849	0.4403	0.5276	0.1598	0.5196	0.3342	0.2110	0.1585	0.8119	0.1790	0.2887	0.4211	0.3067	0.3495
1.7223	87000	9.6789	9.7084	0.1744	0.4400	0.5367	0.1572	0.5068	0.3289	0.2088	0.1622	0.8087	0.1750	0.2886	0.4340	0.3095	0.3485
1.7421	88000	9.6939	9.7020	0.1736	0.4400	0.5423	0.1644	0.5125	0.3339	0.2064	0.1643	0.8052	0.1869	0.2921	0.4120	0.3091	0.3494
1.7619	89000	9.661	9.6965	0.1651	0.4404	0.5433	0.1625	0.5234	0.3362	0.2103	0.1682	0.8052	0.1797	0.2823	0.4291	0.3052	0.3501
1.7816	90000	9.6624	9.6919	0.1689	0.4438	0.5317	0.1496	0.5125	0.3421	0.2056	0.1643	0.8078	0.1750	0.3034	0.4187	0.3003	0.3480
1.8014	91000	9.666	9.6855	0.1719	0.4468	0.5395	0.1572	0.5188	0.3430	0.2032	0.1506	0.8065	0.1795	0.2888	0.4185	0.2940	0.3476
1.8212	92000	9.6715	9.6823	0.1703	0.4456	0.5311	0.1568	0.5193	0.3530	0.2046	0.1635	0.7988	0.1758	0.2951	0.4236	0.2994	0.3490
1.8410	93000	9.6597	9.6800	0.1703	0.4491	0.5255	0.1622	0.5194	0.3491	0.2137	0.1444	0.8062	0.1728	0.3083	0.4199	0.3070	0.3498
1.8608	94000	9.6594	9.6740	0.1668	0.4469	0.5233	0.1536	0.5194	0.3396	0.2077	0.1586	0.8095	0.1809	0.2895	0.4238	0.3000	0.3477
1.8806	95000	9.6565	9.6647	0.1738	0.4461	0.5312	0.1502	0.5392	0.3444	0.2074	0.1555	0.8063	0.1823	0.2979	0.4282	0.3023	0.3511
1.9004	96000	9.6476	9.6640	0.1759	0.4456	0.5433	0.1565	0.5318	0.3470	0.2149	0.1548	0.8047	0.1717	0.3024	0.4359	0.2953	0.3523
1.9202	97000	9.6588	9.6563	0.1815	0.4449	0.5431	0.1617	0.5267	0.3460	0.2061	0.1557	0.8068	0.1667	0.2997	0.4463	0.3066	0.3532
1.9400	98000	9.6232	9.6491	0.1769	0.4426	0.5411	0.1562	0.5255	0.3430	0.2074	0.1534	0.8108	0.1686	0.2991	0.4395	0.2915	0.3504
1.9598	99000	9.6412	9.6446	0.1722	0.4434	0.5368	0.1652	0.5236	0.3378	0.1998	0.1533	0.8043	0.1670	0.3053	0.4498	0.2899	0.3499
1.9796	100000	9.6418	9.6400	0.1740	0.4444	0.5379	0.1635	0.5284	0.3340	0.2038	0.1682	0.8013	0.1780	0.3077	0.4224	0.2877	0.3501
1.9994	101000	9.6363	9.6378	0.1784	0.4439	0.5349	0.1626	0.5273	0.3432	0.2168	0.1602	0.8028	0.1797	0.2987	0.4336	0.2999	0.3525
2.0192	102000	9.5424	9.6456	0.1817	0.4450	0.5436	0.1563	0.5333	0.3374	0.2124	0.1551	0.8045	0.1767	0.2880	0.4329	0.2923	0.3507
2.0390	103000	9.5632	9.6461	0.1818	0.4505	0.5405	0.1566	0.5251	0.3387	0.2047	0.1533	0.7995	0.1697	0.2860	0.4399	0.2936	0.3492
2.0588	104000	9.5526	9.6401	0.1775	0.4386	0.5245	0.1471	0.5212	0.3383	0.2110	0.1548	0.8061	0.1663	0.2945	0.4264	0.2995	0.3466
2.0786	105000	9.5694	9.6374	0.1915	0.4489	0.5283	0.1506	0.5276	0.3393	0.2016	0.1498	0.8045	0.1723	0.2938	0.4376	0.3007	0.3497
2.0984	106000	9.5772	9.6314	0.1728	0.4530	0.5356	0.1605	0.5278	0.3358	0.2061	0.1503	0.8050	0.1734	0.3016	0.4274	0.2991	0.3499
2.1182	107000	9.5735	9.6322	0.1711	0.4380	0.5450	0.1618	0.5333	0.3462	0.2026	0.1591	0.8057	0.1711	0.3005	0.4159	0.2984	0.3499
2.1380	108000	9.5764	9.6262	0.1738	0.4547	0.5394	0.1548	0.5330	0.3372	0.2003	0.1589	0.8026	0.1768	0.2914	0.4384	0.2877	0.3499
2.1578	109000	9.5918	9.6217	0.1699	0.4404	0.5272	0.1469	0.5248	0.3483	0.2020	0.1507	0.8006	0.1771	0.2851	0.4183	0.3009	0.3456
2.1776	110000	9.5565	9.6192	0.1700	0.4443	0.5291	0.1477	0.5296	0.3409	0.2072	0.1530	0.8042	0.1752	0.2823	0.4203	0.2976	0.3463
2.1974	111000	9.5725	9.6153	0.1733	0.4434	0.5258	0.1499	0.5215	0.3397	0.1976	0.1544	0.8031	0.1830	0.2749	0.4255	0.2939	0.3451
2.2172	112000	9.552	9.6102	0.1765	0.4440	0.5258	0.1539	0.5315	0.3397	0.1998	0.1561	0.8026	0.1833	0.2790	0.4262	0.2914	0.3469
2.2370	113000	9.5574	9.6062	0.1810	0.4425	0.5363	0.1573	0.5344	0.3341	0.2008	0.1549	0.8016	0.1767	0.2808	0.4411	0.2972	0.3491
2.2568	114000	9.5671	9.6021	0.1837	0.4423	0.5330	0.1547	0.5164	0.3357	0.2062	0.1572	0.7990	0.1733	0.2852	0.4280	0.2894	0.3465
2.2766	115000	9.5393	9.6005	0.1857	0.4413	0.5339	0.1639	0.5091	0.3312	0.2057	0.1547	0.8018	0.1820	0.2761	0.4236	0.2909	0.3462
2.2963	116000	9.5581	9.5972	0.1807	0.4443	0.5454	0.1488	0.5168	0.3191	0.2154	0.1558	0.8021	0.1770	0.2949	0.4140	0.2945	0.3468
2.3161	117000	9.5702	9.5921	0.1804	0.4424	0.5471	0.1499	0.5147	0.3227	0.2109	0.1461	0.8018	0.1783	0.3053	0.4120	0.2889	0.3462
2.3359	118000	9.5395	9.5915	0.1756	0.4371	0.5301	0.1582	0.5210	0.3224	0.2090	0.1507	0.7967	0.1780	0.2988	0.4034	0.2933	0.3442
2.3557	119000	9.5434	9.5855	0.1735	0.4458	0.5441	0.1566	0.5253	0.3281	0.2098	0.1517	0.7965	0.1736	0.3016	0.4166	0.2859	0.3468
2.3755	120000	9.5444	9.5812	0.1709	0.4490	0.5432	0.1534	0.5174	0.3308	0.2043	0.1503	0.7965	0.1748	0.2895	0.4206	0.2802	0.3447
2.3953	121000	9.5562	9.5739	0.1779	0.4413	0.5380	0.1467	0.5184	0.3371	0.2057	0.1511	0.7974	0.1821	0.2815	0.4202	0.2856	0.3448
2.4151	122000	9.5334	9.5738	0.1802	0.4385	0.5357	0.1537	0.5149	0.3361	0.2151	0.1503	0.7975	0.1836	0.3001	0.4133	0.2822	0.3463
2.4349	123000	9.5202	9.5696	0.1697	0.4451	0.5411	0.1493	0.5216	0.3337	0.2116	0.1488	0.7965	0.1804	0.2903	0.4231	0.2908	0.3463
2.4547	124000	9.5296	9.5683	0.1711	0.4556	0.5306	0.1466	0.5181	0.3235	0.2141	0.1570	0.7965	0.1785	0.2984	0.4201	0.2929	0.3464
2.4745	125000	9.5399	9.5660	0.1791	0.4487	0.5275	0.1417	0.5264	0.3305	0.2209	0.1596	0.7977	0.1770	0.3013	0.4271	0.2833	0.3478
2.4943	126000	9.5583	9.5641	0.1708	0.4400	0.5341	0.1489	0.5198	0.3291	0.2107	0.1515	0.8003	0.1784	0.3049	0.4282	0.2871	0.3465
2.5141	127000	9.5252	9.5618	0.1756	0.4424	0.5408	0.1577	0.5209	0.3244	0.2130	0.1526	0.8015	0.1785	0.3094	0.4217	0.2849	0.3480
2.5339	128000	9.5122	9.5577	0.1748	0.4405	0.5383	0.1501	0.5188	0.3305	0.2102	0.1446	0.8041	0.1804	0.3074	0.4184	0.2943	0.3471
2.5537	129000	9.5237	9.5523	0.1754	0.4396	0.5369	0.1509	0.5269	0.3246	0.2117	0.1458	0.8026	0.1799	0.2997	0.4153	0.2947	0.3465
2.5735	130000	9.5257	9.5510	0.1705	0.4365	0.5369	0.1560	0.5302	0.3310	0.2087	0.1559	0.8015	0.1832	0.3070	0.4243	0.2955	0.3490
2.5933	131000	9.5407	9.5489	0.1704	0.4386	0.5350	0.1495	0.5323	0.3302	0.2123	0.1565	0.8012	0.1846	0.3027	0.4278	0.2997	0.3493
2.6131	132000	9.5339	9.5449	0.1693	0.4445	0.5416	0.1621	0.5170	0.3186	0.2105	0.1551	0.8018	0.1799	0.2952	0.4263	0.2969	0.3476
2.6329	133000	9.5095	9.5399	0.1697	0.4392	0.5416	0.1545	0.5140	0.3332	0.2090	0.1557	0.7995	0.1758	0.2920	0.4202	0.3030	0.3467
2.6527	134000	9.5319	9.5397	0.1743	0.4370	0.5427	0.1635	0.5250	0.3231	0.2076	0.1504	0.8012	0.1767	0.2909	0.4205	0.2920	0.3465
2.6725	135000	9.5018	9.5376	0.1698	0.4358	0.5316	0.1600	0.5249	0.3199	0.2058	0.1496	0.8012	0.1859	0.2939	0.4150	0.2945	0.3452
2.6923	136000	9.4906	9.5338	0.1762	0.4350	0.5308	0.1525	0.5226	0.3315	0.2108	0.1667	0.7995	0.1809	0.2830	0.4364	0.2952	0.3478
2.7121	137000	9.4951	9.5307	0.1745	0.4356	0.5385	0.1482	0.5183	0.3339	0.2103	0.1658	0.7995	0.1786	0.2899	0.4205	0.2943	0.3468
2.7319	138000	9.498	9.5292	0.1710	0.4353	0.5363	0.1504	0.5278	0.3377	0.2045	0.1586	0.7981	0.1885	0.2882	0.4145	0.2996	0.3470
2.7517	139000	9.5133	9.5262	0.1705	0.4336	0.5352	0.1514	0.5250	0.3233	0.2091	0.1604	0.8016	0.1854	0.2837	0.4188	0.2966	0.3457
2.7715	140000	9.4934	9.5222	0.1740	0.4378	0.5279	0.1539	0.5199	0.3302	0.2128	0.1554	0.7989	0.1799	0.2885	0.4224	0.3013	0.3464
2.7913	141000	9.4993	9.5188	0.1754	0.4353	0.5209	0.1504	0.5287	0.3284	0.2128	0.1503	0.7972	0.1853	0.2851	0.4239	0.2956	0.3453
2.8110	142000	9.498	9.5188	0.1763	0.4313	0.5328	0.1514	0.5203	0.3260	0.2068	0.1603	0.8016	0.1812	0.3041	0.4303	0.2892	0.3470
2.8308	143000	9.477	9.5174	0.1749	0.4281	0.5437	0.1515	0.5096	0.3183	0.2025	0.1524	0.7963	0.1897	0.2938	0.4315	0.2872	0.3446
2.8506	144000	9.483	9.5132	0.1768	0.4279	0.5361	0.1424	0.5181	0.3307	0.2046	0.1506	0.7969	0.1834	0.2965	0.4301	0.2885	0.3448
2.8704	145000	9.478	9.5092	0.1870	0.4299	0.5334	0.1450	0.5128	0.3299	0.2035	0.1488	0.7981	0.1792	0.3008	0.4289	0.2886	0.3451
2.8902	146000	9.4904	9.5053	0.1759	0.4279	0.5370	0.1438	0.5218	0.3271	0.2077	0.1537	0.7995	0.1847	0.2832	0.4269	0.2891	0.3445
2.9100	147000	9.4787	9.5035	0.1744	0.4281	0.5437	0.1597	0.5050	0.3377	0.2044	0.1499	0.8003	0.1898	0.2915	0.4273	0.2928	0.3465
2.9298	148000	9.4861	9.5041	0.1801	0.4294	0.5303	0.1586	0.5067	0.3178	0.2086	0.1492	0.8030	0.1803	0.2837	0.4160	0.2972	0.3431
2.9496	149000	9.4736	9.5001	0.1758	0.4249	0.5350	0.1515	0.5103	0.3258	0.2128	0.1463	0.7983	0.1785	0.2847	0.4281	0.2936	0.3435
2.9694	150000	9.4847	9.4980	0.1742	0.4305	0.5362	0.1524	0.5215	0.3250	0.2097	0.1485	0.8016	0.1768	0.2911	0.4228	0.2946	0.3450
2.9892	151000	9.4756	9.4948	0.1694	0.4270	0.5333	0.1575	0.5128	0.3191	0.2116	0.1445	0.8015	0.1736	0.2908	0.4215	0.2889	0.3424
3.0090	152000	9.4206	9.4949	0.1751	0.4243	0.5332	0.1432	0.5094	0.3172	0.2100	0.1442	0.7981	0.1763	0.2852	0.4310	0.2880	0.3412
3.0288	153000	9.3728	9.4973	0.1746	0.4330	0.5332	0.1447	0.5212	0.3211	0.2142	0.1493	0.7968	0.1803	0.2964	0.4287	0.2886	0.3448
3.0486	154000	9.3962	9.5003	0.1815	0.4325	0.5341	0.1456	0.5162	0.3300	0.2175	0.1431	0.7971	0.1806	0.3010	0.4328	0.2892	0.3462
3.0684	155000	9.3975	9.4988	0.1784	0.4276	0.5391	0.1478	0.5187	0.3271	0.2212	0.1457	0.7987	0.1832	0.3011	0.4305	0.2866	0.3466
3.0882	156000	9.411	9.4975	0.1728	0.4266	0.5301	0.1505	0.5208	0.3275	0.2191	0.1461	0.7994	0.1829	0.3012	0.4289	0.2916	0.3460
3.1080	157000	9.3958	9.4955	0.1796	0.4283	0.5375	0.1498	0.5186	0.3409	0.2209	0.1503	0.7985	0.1816	0.3024	0.4372	0.2875	0.3487
3.1278	158000	9.4203	9.4925	0.1699	0.4338	0.5324	0.1454	0.5078	0.3324	0.2152	0.1480	0.7990	0.1780	0.2957	0.4364	0.2849	0.3445
3.1476	159000	9.416	9.4913	0.1751	0.4325	0.5301	0.1498	0.5152	0.3270	0.2179	0.1491	0.7964	0.1782	0.3020	0.4285	0.2878	0.3454
3.1674	160000	9.4133	9.4867	0.1757	0.4320	0.5334	0.1528	0.5177	0.3264	0.2153	0.1443	0.7896	0.1784	0.2946	0.4276	0.2933	0.3447
3.1872	161000	9.4188	9.4860	0.1780	0.4300	0.5357	0.1486	0.5096	0.3295	0.2221	0.1479	0.7915	0.1780	0.2941	0.4224	0.2920	0.3446
3.2070	162000	9.4297	9.4831	0.1826	0.4291	0.5338	0.1520	0.5032	0.3359	0.2204	0.1488	0.7951	0.1759	0.2946	0.4272	0.2887	0.3452
3.2268	163000	9.4151	9.4808	0.1779	0.4341	0.5256	0.1517	0.5141	0.3407	0.2200	0.1460	0.7973	0.1854	0.2971	0.4191	0.2903	0.3461
3.2466	164000	9.4185	9.4781	0.1748	0.4358	0.5368	0.1409	0.5137	0.3376	0.2139	0.1414	0.7974	0.1759	0.3024	0.4214	0.2890	0.3447
3.2664	165000	9.4227	9.4763	0.1771	0.4319	0.5236	0.1389	0.5143	0.3389	0.2091	0.1515	0.7960	0.1800	0.2955	0.4286	0.2896	0.3442
3.2862	166000	9.4049	9.4711	0.1804	0.4312	0.5264	0.1449	0.5098	0.3393	0.2083	0.1505	0.7963	0.1811	0.2918	0.4278	0.2897	0.3444
3.3059	167000	9.4249	9.4675	0.1788	0.4297	0.5298	0.1395	0.5121	0.3463	0.2096	0.1455	0.7975	0.1810	0.3020	0.4351	0.2882	0.3458
3.3257	168000	9.4047	9.4667	0.1660	0.4296	0.5296	0.1427	0.5152	0.3488	0.2093	0.1458	0.7975	0.1830	0.3008	0.4352	0.2869	0.3454
3.3455	169000	9.4124	9.4663	0.1661	0.4260	0.5325	0.1439	0.5171	0.3550	0.2122	0.1444	0.7975	0.1833	0.2994	0.4352	0.2891	0.3463
3.3653	170000	9.416	9.4636	0.1729	0.4248	0.5424	0.1578	0.5146	0.3521	0.2078	0.1463	0.7975	0.1783	0.3047	0.4292	0.2883	0.3474
3.3851	171000	9.4139	9.4593	0.1732	0.4275	0.5390	0.1517	0.5233	0.3433	0.2079	0.1477	0.7975	0.1750	0.3052	0.4285	0.2865	0.3466
3.4049	172000	9.3927	9.4585	0.1771	0.4279	0.5339	0.1522	0.5226	0.3456	0.2095	0.1468	0.7981	0.1791	0.3029	0.4300	0.2851	0.3470
3.4247	173000	9.4008	9.4560	0.1753	0.4289	0.5344	0.1606	0.5179	0.3410	0.2068	0.1467	0.7975	0.1796	0.2984	0.4294	0.2869	0.3464
3.4445	174000	9.403	9.4545	0.1730	0.4337	0.5372	0.1535	0.5230	0.3296	0.2030	0.1470	0.8010	0.1802	0.3080	0.4243	0.2879	0.3463
3.4643	175000	9.414	9.4498	0.1678	0.4330	0.5383	0.1588	0.5134	0.3348	0.2050	0.1472	0.7984	0.1794	0.2980	0.4165	0.2876	0.3445
3.4841	176000	9.4006	9.4484	0.1726	0.4367	0.5311	0.1571	0.5167	0.3191	0.2092	0.1517	0.7975	0.1840	0.2968	0.4212	0.2904	0.3449
3.5039	177000	9.4065	9.4452	0.1722	0.4347	0.5311	0.1524	0.5210	0.3324	0.2061	0.1525	0.7964	0.1810	0.3090	0.4310	0.2895	0.3469
3.5237	178000	9.4145	9.4411	0.1763	0.4360	0.5279	0.1571	0.5112	0.3257	0.2094	0.1505	0.7969	0.1768	0.2963	0.4288	0.2883	0.3447
3.5435	179000	9.4052	9.4404	0.1757	0.4367	0.5292	0.1549	0.5200	0.3348	0.2107	0.1527	0.7961	0.1808	0.2873	0.4250	0.2871	0.3455
3.5633	180000	9.412	9.4392	0.1723	0.4337	0.5354	0.1531	0.5181	0.3348	0.2092	0.1480	0.7967	0.1786	0.2877	0.4227	0.2907	0.3447
3.5831	181000	9.4105	9.4377	0.1747	0.4308	0.5334	0.1572	0.5188	0.3348	0.2101	0.1480	0.7967	0.1753	0.2894	0.4294	0.2895	0.3452
3.6029	182000	9.3904	9.4336	0.1703	0.4358	0.5354	0.1524	0.5229	0.3283	0.2227	0.1488	0.7999	0.1768	0.2954	0.4290	0.2889	0.3467
3.6227	183000	9.3784	9.4310	0.1743	0.4311	0.5379	0.1437	0.5182	0.3264	0.2198	0.1490	0.7999	0.1758	0.3012	0.4294	0.2889	0.3458
3.6425	184000	9.3762	9.4288	0.1713	0.4345	0.5362	0.1506	0.5136	0.3186	0.2107	0.1491	0.7973	0.1751	0.3018	0.4282	0.2898	0.3444
3.6623	185000	9.3958	9.4268	0.1757	0.4290	0.5420	0.1503	0.5158	0.3175	0.2067	0.1465	0.7938	0.1772	0.3020	0.4219	0.2921	0.3439
3.6821	186000	9.4056	9.4261	0.1790	0.4308	0.5388	0.1454	0.5162	0.3200	0.2096	0.1400	0.7949	0.1699	0.2988	0.4235	0.2867	0.3426
3.7019	187000	9.3616	9.4244	0.1797	0.4279	0.5428	0.1499	0.5173	0.3252	0.2150	0.1405	0.7975	0.1758	0.2900	0.4287	0.2862	0.3443
3.7217	188000	9.3864	9.4239	0.1794	0.4288	0.5447	0.1474	0.5225	0.3273	0.2210	0.1467	0.7975	0.1710	0.2966	0.4361	0.2804	0.3461
3.7415	189000	9.3842	9.4199	0.1765	0.4295	0.5306	0.1450	0.5176	0.3190	0.2218	0.1461	0.7961	0.1753	0.2959	0.4284	0.2843	0.3436
3.7613	190000	9.3888	9.4186	0.1770	0.4281	0.5369	0.1451	0.5140	0.3171	0.2173	0.1408	0.7953	0.1774	0.2887	0.4271	0.2833	0.3422
3.7811	191000	9.3769	9.4163	0.1777	0.4291	0.5417	0.1411	0.5150	0.3176	0.2103	0.1474	0.7959	0.1813	0.3013	0.4268	0.2757	0.3431
3.8009	192000	9.3643	9.4151	0.1773	0.4275	0.5396	0.1483	0.5170	0.3236	0.2100	0.1482	0.7959	0.1796	0.2993	0.4274	0.2766	0.3439
3.8206	193000	9.376	9.4128	0.1707	0.4300	0.5431	0.1422	0.5139	0.3277	0.2144	0.1472	0.7959	0.1823	0.2945	0.4283	0.2821	0.3440
3.8404	194000	9.396	9.4102	0.1727	0.4280	0.5418	0.1486	0.5137	0.3242	0.2071	0.1470	0.7959	0.1800	0.3001	0.4280	0.2843	0.3440
3.8602	195000	9.3662	9.4087	0.1741	0.4273	0.5371	0.1451	0.5116	0.3185	0.2101	0.1455	0.7959	0.1810	0.2940	0.4278	0.2840	0.3424
3.8800	196000	9.3727	9.4067	0.1704	0.4271	0.5393	0.1411	0.5099	0.3165	0.2047	0.1508	0.7967	0.1848	0.2946	0.4281	0.2838	0.3421
3.8998	197000	9.3805	9.4048	0.1716	0.4254	0.5416	0.1477	0.5192	0.3154	0.2098	0.1468	0.7953	0.1827	0.2920	0.4280	0.2874	0.3433
3.9196	198000	9.3799	9.4033	0.1687	0.4278	0.5393	0.1472	0.5146	0.3219	0.2083	0.1479	0.7961	0.1838	0.2918	0.4275	0.2860	0.3432
3.9394	199000	9.3702	9.3999	0.1681	0.4306	0.5401	0.1476	0.5098	0.3233	0.2112	0.1470	0.7975	0.1816	0.2926	0.4278	0.2814	0.3430
3.9592	200000	9.3646	9.3988	0.1701	0.4321	0.5401	0.1484	0.5107	0.3227	0.2135	0.1465	0.7980	0.1815	0.2930	0.4335	0.2858	0.3443
3.9790	201000	9.3559	9.3963	0.1696	0.4319	0.5418	0.1475	0.5135	0.3218	0.2117	0.1484	0.7975	0.1821	0.2856	0.4270	0.2853	0.3434
3.9988	202000	9.3566	9.3950	0.1743	0.4284	0.5432	0.1398	0.5092	0.3236	0.2113	0.1481	0.7980	0.1822	0.2784	0.4330	0.2827	0.3425
4.0186	203000	9.2801	9.3988	0.1709	0.4305	0.5418	0.1357	0.5223	0.3149	0.2129	0.1513	0.7975	0.1804	0.2873	0.4349	0.2820	0.3433
4.0384	204000	9.3024	9.3985	0.1745	0.4305	0.5418	0.1451	0.5189	0.3159	0.2081	0.1501	0.7975	0.1795	0.2869	0.4284	0.2828	0.3431
4.0582	205000	9.2953	9.3992	0.1743	0.4278	0.5418	0.1327	0.5162	0.3145	0.2110	0.1498	0.7975	0.1843	0.2818	0.4289	0.2825	0.3418
4.0780	206000	9.2922	9.4003	0.1731	0.4283	0.5416	0.1391	0.5180	0.3166	0.2110	0.1498	0.7972	0.1801	0.2796	0.4289	0.2830	0.3420
4.0978	207000	9.2851	9.3996	0.1740	0.4294	0.5416	0.1410	0.5147	0.3155	0.2134	0.1560	0.7975	0.1822	0.2880	0.4303	0.2820	0.3435
4.1176	208000	9.2913	9.3978	0.1740	0.4325	0.5416	0.1350	0.5131	0.3156	0.2129	0.1554	0.7975	0.1800	0.2876	0.4303	0.2856	0.3432
4.1374	209000	9.298	9.3966	0.1732	0.4274	0.5430	0.1387	0.5219	0.3139	0.2145	0.1507	0.7975	0.1779	0.2870	0.4275	0.2852	0.3430
4.1572	210000	9.2952	9.3943	0.1761	0.4262	0.5430	0.1433	0.5226	0.3231	0.2128	0.1561	0.7980	0.1806	0.2871	0.4282	0.2865	0.3449
4.1770	211000	9.3193	9.3924	0.1741	0.4269	0.5430	0.1331	0.5218	0.3256	0.2140	0.1503	0.7980	0.1786	0.2869	0.4284	0.2843	0.3435
4.1968	212000	9.297	9.3912	0.1744	0.4278	0.5428	0.1427	0.5217	0.3267	0.2138	0.1488	0.7980	0.1794	0.2806	0.4278	0.2831	0.3437
4.2166	213000	9.2984	9.3891	0.1797	0.4297	0.5430	0.1428	0.5236	0.3251	0.2128	0.1495	0.7980	0.1762	0.2791	0.4272	0.2859	0.3440
4.2364	214000	9.306	9.3881	0.1818	0.4275	0.5436	0.1457	0.5215	0.3244	0.2120	0.1498	0.7980	0.1812	0.2801	0.4278	0.2835	0.3444
4.2562	215000	9.3029	9.3861	0.1807	0.4290	0.5436	0.1413	0.5206	0.3244	0.2166	0.1481	0.7980	0.1829	0.2860	0.4275	0.2847	0.3449
4.2760	216000	9.2965	9.3848	0.1769	0.4280	0.5430	0.1471	0.5209	0.3251	0.2128	0.1555	0.7975	0.1794	0.2739	0.4270	0.2827	0.3438
4.2958	217000	9.3171	9.3828	0.1796	0.4285	0.5430	0.1438	0.5209	0.3231	0.2133	0.1490	0.7975	0.1819	0.2858	0.4270	0.2793	0.3440
4.3155	218000	9.3181	9.3824	0.1794	0.4262	0.5430	0.1496	0.5241	0.3243	0.2147	0.1481	0.7975	0.1794	0.2812	0.4275	0.2818	0.3444
4.3353	219000	9.2952	9.3794	0.1766	0.4265	0.5432	0.1412	0.5223	0.3243	0.2098	0.1475	0.7975	0.1777	0.2851	0.4328	0.2784	0.3433
4.3551	220000	9.32	9.3776	0.1739	0.4261	0.5432	0.1362	0.5258	0.3257	0.2106	0.1470	0.7980	0.1782	0.2815	0.4268	0.2787	0.3424
4.3749	221000	9.2999	9.3758	0.1767	0.4297	0.5432	0.1395	0.5175	0.3252	0.2126	0.1489	0.7980	0.1778	0.2865	0.4210	0.2801	0.3428
4.3947	222000	9.2954	9.3750	0.1783	0.4261	0.5432	0.1397	0.5220	0.3244	0.2116	0.1496	0.7980	0.1797	0.2929	0.4268	0.2786	0.3439
4.4145	223000	9.2944	9.3726	0.1795	0.4275	0.5432	0.1395	0.5172	0.3236	0.2130	0.1488	0.7971	0.1785	0.2921	0.4273	0.2796	0.3436
4.4343	224000	9.2851	9.3714	0.1794	0.4251	0.5432	0.1395	0.5172	0.3227	0.2136	0.1488	0.7975	0.1780	0.2921	0.4268	0.2788	0.3433
4.4541	225000	9.2856	9.3694	0.1761	0.4257	0.5432	0.1408	0.5218	0.3227	0.2116	0.1486	0.7971	0.1800	0.2935	0.4270	0.2794	0.3437
4.4739	226000	9.2967	9.3676	0.1792	0.4256	0.5418	0.1372	0.5200	0.3230	0.2100	0.1492	0.7967	0.1774	0.2939	0.4270	0.2803	0.3432
4.4937	227000	9.3019	9.3670	0.1798	0.4253	0.5430	0.1397	0.5200	0.3147	0.2063	0.1481	0.7967	0.1779	0.2946	0.4210	0.2792	0.3420
4.5135	228000	9.2938	9.3655	0.1795	0.4258	0.5423	0.1397	0.5192	0.3139	0.2094	0.1487	0.7967	0.1775	0.2943	0.4210	0.2780	0.3420
4.5333	229000	9.306	9.3643	0.1772	0.4251	0.5432	0.1393	0.5235	0.3148	0.2079	0.1487	0.7998	0.1798	0.2917	0.4216	0.2768	0.3423
4.5531	230000	9.3057	9.3631	0.1726	0.4250	0.5423	0.1393	0.5241	0.3148	0.2080	0.1483	0.7967	0.1795	0.2923	0.4216	0.2771	0.3417
4.5729	231000	9.3069	9.3615	0.1757	0.4240	0.5421	0.1500	0.5226	0.3171	0.2093	0.1481	0.7980	0.1783	0.2920	0.4216	0.2784	0.3429
4.5927	232000	9.3003	9.3604	0.1752	0.4255	0.5421	0.1498	0.5226	0.3185	0.2096	0.1478	0.7980	0.1801	0.2920	0.4216	0.2783	0.3432
4.6125	233000	9.3042	9.3594	0.1748	0.4243	0.5407	0.1453	0.5263	0.3185	0.2098	0.1472	0.7972	0.1796	0.2918	0.4216	0.2797	0.3428
4.6323	234000	9.3079	9.3573	0.1749	0.4256	0.5407	0.1428	0.5242	0.3185	0.2096	0.1536	0.7975	0.1793	0.2920	0.4273	0.2815	0.3437
4.6521	235000	9.284	9.3566	0.1729	0.4256	0.5407	0.1455	0.5253	0.3190	0.2079	0.1487	0.7975	0.1801	0.2936	0.4273	0.2812	0.3435
4.6719	236000	9.2916	9.3550	0.1755	0.4270	0.5416	0.1447	0.5216	0.3190	0.2081	0.1487	0.7975	0.1797	0.2869	0.4273	0.2823	0.3431
4.6917	237000	9.2871	9.3537	0.1733	0.4263	0.5421	0.1447	0.5246	0.3190	0.2097	0.1492	0.7980	0.1779	0.2917	0.4273	0.2786	0.3433
4.7115	238000	9.3105	9.3519	0.1729	0.4248	0.5430	0.1372	0.5194	0.3176	0.2096	0.1492	0.7980	0.1803	0.2917	0.4273	0.2799	0.3424
4.7313	239000	9.2935	9.3506	0.1731	0.4241	0.5421	0.1447	0.5194	0.3176	0.2078	0.1483	0.7975	0.1780	0.2903	0.4273	0.2797	0.3423
4.7511	240000	9.283	9.3497	0.1730	0.4257	0.5421	0.1388	0.5149	0.3176	0.2079	0.1486	0.7975	0.1779	0.2906	0.4273	0.2809	0.3417
4.7709	241000	9.2994	9.3486	0.1733	0.4257	0.5421	0.1388	0.5194	0.3176	0.2093	0.1486	0.7959	0.1798	0.2903	0.4216	0.2785	0.3416
4.7907	242000	9.2784	9.3475	0.1734	0.4245	0.5421	0.1433	0.5149	0.3176	0.2078	0.1486	0.7966	0.1780	0.2899	0.4200	0.2797	0.3413
4.8105	243000	9.2968	9.3466	0.1751	0.4245	0.5421	0.1388	0.5149	0.3176	0.2083	0.1486	0.7980	0.1779	0.2906	0.4273	0.2768	0.3416
4.8302	244000	9.2829	9.3455	0.1751	0.4245	0.5421	0.1446	0.5149	0.3176	0.2096	0.1486	0.7959	0.1778	0.2899	0.4273	0.2782	0.3420
4.8500	245000	9.2787	9.3449	0.1739	0.4245	0.5421	0.1446	0.5149	0.3176	0.2085	0.1486	0.7961	0.1779	0.2899	0.4273	0.2794	0.3420
4.8698	246000	9.2856	9.3439	0.1735	0.4247	0.5421	0.1491	0.5149	0.3176	0.2081	0.1483	0.7961	0.1779	0.2899	0.4216	0.2806	0.3419
4.8896	247000	9.2754	9.3433	0.1735	0.4247	0.5421	0.1490	0.5149	0.3176	0.2083	0.1483	0.7966	0.1779	0.2897	0.4216	0.2810	0.3419
4.9094	248000	9.2706	9.3427	0.1735	0.4247	0.5421	0.1491	0.5140	0.3176	0.2066	0.1487	0.7959	0.1774	0.2899	0.4216	0.2825	0.3418
4.9292	249000	9.3004	9.3422	0.1735	0.4247	0.5416	0.1491	0.5140	0.3176	0.2066	0.1487	0.7975	0.1774	0.2899	0.4216	0.2811	0.3418
4.9490	250000	9.2861	9.3417	0.1735	0.4247	0.5416	0.1491	0.5140	0.3176	0.2066	0.1487	0.7961	0.1774	0.2899	0.4216	0.2811	0.3417
4.9688	251000	9.2583	9.3412	0.1735	0.4247	0.5416	0.1491	0.5140	0.3176	0.2066	0.1487	0.7966	0.1755	0.2899	0.4216	0.2813	0.3416
4.9886	252000	9.2786	9.3411	0.1735	0.4247	0.5416	0.1491	0.5140	0.3176	0.2066	0.1483	0.7966	0.1755	0.2899	0.4216	0.2813	0.3416

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.3.1
Transformers: 4.48.0
PyTorch: 2.5.1+cu124
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@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

@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

@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}
}