README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:99231
  - loss:CachedMultipleNegativesRankingLoss
widget:
  - source_sentence: who ordered the charge of the light brigade
    sentences:
      - >-
        Charge of the Light Brigade The Charge of the Light Brigade was a charge
        of British light cavalry led by Lord Cardigan against Russian forces
        during the Battle of Balaclava on 25 October 1854 in the Crimean War.
        Lord Raglan, overall commander of the British forces, had intended to
        send the Light Brigade to prevent the Russians from removing captured
        guns from overrun Turkish positions, a task well-suited to light
        cavalry.
      - >-
        UNICEF The United Nations International Children's Emergency Fund was
        created by the United Nations General Assembly on 11 December 1946, to
        provide emergency food and healthcare to children in countries that had
        been devastated by World War II. The Polish physician Ludwik Rajchman is
        widely regarded as the founder of UNICEF and served as its first
        chairman from 1946. On Rajchman's suggestion, the American Maurice Pate
        was appointed its first executive director, serving from 1947 until his
        death in 1965.[5][6] In 1950, UNICEF's mandate was extended to address
        the long-term needs of children and women in developing countries
        everywhere. In 1953 it became a permanent part of the United Nations
        System, and the words "international" and "emergency" were dropped from
        the organization's name, making it simply the United Nations Children's
        Fund, retaining the original acronym, "UNICEF".[3]
      - >-
        Marcus Jordan Marcus James Jordan (born December 24, 1990) is an
        American former college basketball player who played for the UCF Knights
        men's basketball team of Conference USA.[1] He is the son of retired
        Hall of Fame basketball player Michael Jordan.
  - source_sentence: what part of the cow is the rib roast
    sentences:
      - >-
        Standing rib roast A standing rib roast, also known as prime rib, is a
        cut of beef from the primal rib, one of the nine primal cuts of beef.
        While the entire rib section comprises ribs six through 12, a standing
        rib roast may contain anywhere from two to seven ribs.
      - >-
        Blaine Anderson Kurt begins to mend their relationship in
        "Thanksgiving", just before New Directions loses at Sectionals to the
        Warblers, and they spend Christmas together in New York City.[29][30]
        Though he and Kurt continue to be on good terms, Blaine finds himself
        developing a crush on his best friend, Sam, which he knows will come to
        nothing as he knows Sam is not gay; the two of them team up to find
        evidence that the Warblers cheated at Sectionals, which means New
        Directions will be competing at Regionals. He ends up going to the Sadie
        Hawkins dance with Tina Cohen-Chang (Jenna Ushkowitz), who has developed
        a crush on him, but as friends only.[31] When Kurt comes to Lima for the
        wedding of glee club director Will (Matthew Morrison) and Emma (Jayma
        Mays)—which Emma flees—he and Blaine make out beforehand, and sleep
        together afterward, though they do not resume a permanent
        relationship.[32]
      - "Soviet Union The Soviet Union (Russian: Сове́тский Сою́з, tr. Sovétsky Soyúz, IPA:\_[sɐˈvʲɛt͡skʲɪj sɐˈjus]\_(\_listen)), officially the Union of Soviet Socialist Republics (Russian: Сою́з Сове́тских Социалисти́ческих Респу́блик, tr. Soyúz Sovétskikh Sotsialistícheskikh Respúblik, IPA:\_[sɐˈjus sɐˈvʲɛtskʲɪx sətsɨəlʲɪsˈtʲitɕɪskʲɪx rʲɪˈspublʲɪk]\_(\_listen)), abbreviated as the USSR (Russian: СССР, tr. SSSR), was a socialist state in Eurasia that existed from 1922 to 1991. Nominally a union of multiple national Soviet republics,[a] its government and economy were highly centralized. The country was a one-party state, governed by the Communist Party with Moscow as its capital in its largest republic, the Russian Soviet Federative Socialist Republic. The Russian nation had constitutionally equal status among the many nations of the union but exerted de facto dominance in various respects.[7] Other major urban centres were Leningrad, Kiev, Minsk, Alma-Ata and Novosibirsk. The Soviet Union was one of the five recognized nuclear weapons states and possessed the largest stockpile of weapons of mass destruction.[8] It was a founding permanent member of the United Nations Security Council, as well as a member of the Organization for Security and Co-operation in Europe (OSCE) and the leading member of the Council for Mutual Economic Assistance (CMEA) and the Warsaw Pact."
  - source_sentence: what is the current big bang theory season
    sentences:
      - >-
        Byzantine army From the seventh to the 12th centuries, the Byzantine
        army was among the most powerful and effective military forces in the
        world – neither Middle Ages Europe nor (following its early successes)
        the fracturing Caliphate could match the strategies and the efficiency
        of the Byzantine army. Restricted to a largely defensive role in the 7th
        to mid-9th centuries, the Byzantines developed the theme-system to
        counter the more powerful Caliphate. From the mid-9th century, however,
        they gradually went on the offensive, culminating in the great conquests
        of the 10th century under a series of soldier-emperors such as
        Nikephoros II Phokas, John Tzimiskes and Basil II. The army they led was
        less reliant on the militia of the themes; it was by now a largely
        professional force, with a strong and well-drilled infantry at its core
        and augmented by a revived heavy cavalry arm. With one of the most
        powerful economies in the world at the time, the Empire had the
        resources to put to the field a powerful host when needed, in order to
        reclaim its long-lost territories.
      - >-
        The Big Bang Theory The Big Bang Theory is an American television sitcom
        created by Chuck Lorre and Bill Prady, both of whom serve as executive
        producers on the series, along with Steven Molaro. All three also serve
        as head writers. The show premiered on CBS on September 24, 2007.[3] The
        series' tenth season premiered on September 19, 2016.[4] In March 2017,
        the series was renewed for two additional seasons, bringing its total to
        twelve, and running through the 2018–19 television season. The
        eleventh season is set to premiere on September 25, 2017.[5]
      - >-
        2016 NCAA Division I Softball Tournament The 2016 NCAA Division I
        Softball Tournament was held from May 20 through June 8, 2016 as the
        final part of the 2016 NCAA Division I softball season. The 64 NCAA
        Division I college softball teams were to be selected out of an eligible
        293 teams on May 15, 2016. Thirty-two teams were awarded an automatic
        bid as champions of their conference, and thirty-two teams were selected
        at-large by the NCAA Division I softball selection committee. The
        tournament culminated with eight teams playing in the 2016 Women's
        College World Series at ASA Hall of Fame Stadium in Oklahoma City in
        which the Oklahoma Sooners were crowned the champions.
  - source_sentence: what happened to tates mom on days of our lives
    sentences:
      - >-
        Paige O'Hara Donna Paige Helmintoller, better known as Paige O'Hara
        (born May 10, 1956),[1] is an American actress, voice actress, singer
        and painter. O'Hara began her career as a Broadway actress in 1983 when
        she portrayed Ellie May Chipley in the musical Showboat. In 1991, she
        made her motion picture debut in Disney's Beauty and the Beast, in which
        she voiced the film's heroine, Belle. Following the critical and
        commercial success of Beauty and the Beast, O'Hara reprised her role as
        Belle in the film's two direct-to-video follow-ups, Beauty and the
        Beast: The Enchanted Christmas and Belle's Magical World.
      - >-
        M. Shadows Matthew Charles Sanders (born July 31, 1981), better known as
        M. Shadows, is an American singer, songwriter, and musician. He is best
        known as the lead vocalist, songwriter, and a founding member of the
        American heavy metal band Avenged Sevenfold. In 2017, he was voted 3rd
        in the list of Top 25 Greatest Modern Frontmen by Ultimate Guitar.[1]
      - >-
        Theresa Donovan In July 2013, Jeannie returns to Salem, this time going
        by her middle name, Theresa. Initially, she strikes up a connection with
        resident bad boy JJ Deveraux (Casey Moss) while trying to secure some
        pot.[28] During a confrontation with JJ and his mother Jennifer Horton
        (Melissa Reeves) in her office, her aunt Kayla confirms that Theresa is
        in fact Jeannie and that Jen promised to hire her as her assistant, a
        promise she reluctantly agrees to. Kayla reminds Theresa it is her last
        chance at a fresh start.[29] Theresa also strikes up a bad first
        impression with Jennifer's daughter Abigail Deveraux (Kate Mansi) when
        Abigail smells pot on Theresa in her mother's office.[30] To continue to
        battle against Jennifer, she teams up with Anne Milbauer (Meredith Scott
        Lynn) in hopes of exacting her perfect revenge. In a ploy, Theresa
        reveals her intentions to hopefully woo Dr. Daniel Jonas (Shawn
        Christian). After sleeping with JJ, Theresa overdoses on marijuana and
        GHB. Upon hearing of their daughter's overdose and continuing problems,
        Shane and Kimberly return to town in the hopes of handling their
        daughter's problem, together. After believing that Theresa has a handle
        on her addictions, Shane and Kimberly leave town together. Theresa then
        teams up with hospital co-worker Anne Milbauer (Meredith Scott Lynn) to
        conspire against Jennifer, using Daniel as a way to hurt their
        relationship. In early 2014, following a Narcotics Anonymous (NA)
        meeting, she begins a sexual and drugged-fused relationship with Brady
        Black (Eric Martsolf). In 2015, after it is found that Kristen DiMera
        (Eileen Davidson) stole Theresa's embryo and carried it to term, Brady
        and Melanie Jonas return her son, Christopher, to her and Brady, and the
        pair rename him Tate. When Theresa moves into the Kiriakis mansion,
        tensions arise between her and Victor. She eventually expresses her
        interest in purchasing Basic Black and running it as her own fashion
        company, with financial backing from Maggie Horton (Suzanne Rogers). In
        the hopes of finding the right partner, she teams up with Kate Roberts
        (Lauren Koslow) and Nicole Walker (Arianne Zucker) to achieve the goal
        of purchasing Basic Black, with Kate and Nicole's business background
        and her own interest in fashion design. As she and Brady share several
        instances of rekindling their romance, she is kicked out of the mansion
        by Victor; as a result, Brady quits Titan and moves in with Theresa and
        Tate, in their own penthouse.
  - source_sentence: where does the last name francisco come from
    sentences:
      - >-
        Francisco Francisco is the Spanish and Portuguese form of the masculine
        given name Franciscus (corresponding to English Francis).
      - >-
        Book of Esther The Book of Esther, also known in Hebrew as "the Scroll"
        (Megillah), is a book in the third section (Ketuvim, "Writings") of the
        Jewish Tanakh (the Hebrew Bible) and in the Christian Old Testament. It
        is one of the five Scrolls (Megillot) in the Hebrew Bible. It relates
        the story of a Hebrew woman in Persia, born as Hadassah but known as
        Esther, who becomes queen of Persia and thwarts a genocide of her
        people. The story forms the core of the Jewish festival of Purim, during
        which it is read aloud twice: once in the evening and again the
        following morning. The books of Esther and Song of Songs are the only
        books in the Hebrew Bible that do not explicitly mention God.[2]
      - >-
        Times Square Times Square is a major commercial intersection, tourist
        destination, entertainment center and neighborhood in the Midtown
        Manhattan section of New York City at the junction of Broadway and
        Seventh Avenue. It stretches from West 42nd to West 47th Streets.[1]
        Brightly adorned with billboards and advertisements, Times Square is
        sometimes referred to as "The Crossroads of the World",[2] "The Center
        of the Universe",[3] "the heart of The Great White Way",[4][5][6] and
        the "heart of the world".[7] One of the world's busiest pedestrian
        areas,[8] it is also the hub of the Broadway Theater District[9] and a
        major center of the world's entertainment industry.[10] Times Square is
        one of the world's most visited tourist attractions, drawing an
        estimated 50 million visitors annually.[11] Approximately 330,000 people
        pass through Times Square daily,[12] many of them tourists,[13] while
        over 460,000 pedestrians walk through Times Square on its busiest
        days.[7]
datasets:
  - sentence-transformers/natural-questions
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
co2_eq_emissions:
  emissions: 405.46378000747745
  energy_consumed: 1.043122443433472
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 3.425
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: LiquidAI/LFM2-350M trained on Natural Questions pairs
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: cosine_accuracy@1
            value: 0.28
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.46
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.64
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.74
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.28
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.128
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07400000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.28
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.46
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.64
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.74
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4909415698599729
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4130714285714285
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.42354966538209315
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: cosine_accuracy@1
            value: 0.4
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.58
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.68
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.35999999999999993
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.324
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.26599999999999996
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.02298357366763854
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.061632366484571384
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.09750915762412557
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.13301219077618073
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.32361002047039217
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.47583333333333333
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12539829347446158
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: cosine_accuracy@1
            value: 0.48
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.68
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.78
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.82
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.48
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.22666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.15600000000000003
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.086
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.47
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.64
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.72
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.78
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.632163202477609
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5983571428571428
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5837963147038205
            name: Cosine Map@100
      - task:
          type: nano-beir
          name: Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: cosine_accuracy@1
            value: 0.3866666666666667
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5466666666666667
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6666666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.7466666666666666
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3866666666666667
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.24666666666666662
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.2026666666666667
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.142
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.25766119122254616
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.38721078882819054
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.48583638587470857
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5510040635920602
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.48223826426932465
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4957539682539682
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.37758142452012505
            name: Cosine Map@100
base_model:
  - LiquidAI/LFM2-350M

LiquidAI/LFM2-350M trained on Natural Questions pairs

This is a sentence-transformers model finetuned from LiquidAI/LFM2-350M on the natural-questions 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: LiquidAI/LFM2-350M
• Maximum Sequence Length: 128000 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • natural-questions
• Language: en
• License: apache-2.0

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128000, 'do_lower_case': False, 'architecture': 'LFM2Model'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, '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': True, 'include_prompt': True})
)

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("tomaarsen/LFM2-350M-nq-prompts")
# Run inference
queries = [
    "where does the last name francisco come from",
]
documents = [
    'Francisco Francisco is the Spanish and Portuguese form of the masculine given name Franciscus (corresponding to English Francis).',
    'Book of Esther The Book of Esther, also known in Hebrew as "the Scroll" (Megillah), is a book in the third section (Ketuvim, "Writings") of the Jewish Tanakh (the Hebrew Bible) and in the Christian Old Testament. It is one of the five Scrolls (Megillot) in the Hebrew Bible. It relates the story of a Hebrew woman in Persia, born as Hadassah but known as Esther, who becomes queen of Persia and thwarts a genocide of her people. The story forms the core of the Jewish festival of Purim, during which it is read aloud twice: once in the evening and again the following morning. The books of Esther and Song of Songs are the only books in the Hebrew Bible that do not explicitly mention God.[2]',
    'Times Square Times Square is a major commercial intersection, tourist destination, entertainment center and neighborhood in the Midtown Manhattan section of New York City at the junction of Broadway and Seventh Avenue. It stretches from West 42nd to West 47th Streets.[1] Brightly adorned with billboards and advertisements, Times Square is sometimes referred to as "The Crossroads of the World",[2] "The Center of the Universe",[3] "the heart of The Great White Way",[4][5][6] and the "heart of the world".[7] One of the world\'s busiest pedestrian areas,[8] it is also the hub of the Broadway Theater District[9] and a major center of the world\'s entertainment industry.[10] Times Square is one of the world\'s most visited tourist attractions, drawing an estimated 50 million visitors annually.[11] Approximately 330,000 people pass through Times Square daily,[12] many of them tourists,[13] while over 460,000 pedestrians walk through Times Square on its busiest days.[7]',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.7825, -0.0811, -0.0414]])

Evaluation

Metrics

Information Retrieval

• Datasets: NanoMSMARCO, NanoNFCorpus and NanoNQ
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "query_prompt": "query: ",
      "corpus_prompt": "document: "
  }
  

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ
cosine_accuracy@1	0.28	0.4	0.48
cosine_accuracy@3	0.46	0.5	0.68
cosine_accuracy@5	0.64	0.58	0.78
cosine_accuracy@10	0.74	0.68	0.82
cosine_precision@1	0.28	0.4	0.48
cosine_precision@3	0.1533	0.36	0.2267
cosine_precision@5	0.128	0.324	0.156
cosine_precision@10	0.074	0.266	0.086
cosine_recall@1	0.28	0.023	0.47
cosine_recall@3	0.46	0.0616	0.64
cosine_recall@5	0.64	0.0975	0.72
cosine_recall@10	0.74	0.133	0.78
cosine_ndcg@10	0.4909	0.3236	0.6322
cosine_mrr@10	0.4131	0.4758	0.5984
cosine_map@100	0.4235	0.1254	0.5838

Nano BEIR

• Dataset: NanoBEIR_mean
• Evaluated with NanoBEIREvaluator with these parameters:

  {
      "dataset_names": [
          "msmarco",
          "nfcorpus",
          "nq"
      ],
      "query_prompts": {
          "msmarco": "query: ",
          "nfcorpus": "query: ",
          "nq": "query: "
      },
      "corpus_prompts": {
          "msmarco": "document: ",
          "nfcorpus": "document: ",
          "nq": "document: "
      }
  }
  

Metric	Value
cosine_accuracy@1	0.3867
cosine_accuracy@3	0.5467
cosine_accuracy@5	0.6667
cosine_accuracy@10	0.7467
cosine_precision@1	0.3867
cosine_precision@3	0.2467
cosine_precision@5	0.2027
cosine_precision@10	0.142
cosine_recall@1	0.2577
cosine_recall@3	0.3872
cosine_recall@5	0.4858
cosine_recall@10	0.551
cosine_ndcg@10	0.4822
cosine_mrr@10	0.4958
cosine_map@100	0.3776

Training Details

Training Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 99,231 training samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 9 tokens mean: 11.59 tokens max: 26 tokens	min: 16 tokens mean: 142.35 tokens max: 559 tokens

• Samples:

  query	answer
  who is required to report according to the hmda	Home Mortgage Disclosure Act US financial institutions must report HMDA data to their regulator if they meet certain criteria, such as having assets above a specific threshold. The criteria is different for depository and non-depository institutions and are available on the FFIEC website.[4] In 2012, there were 7,400 institutions that reported a total of 18.7 million HMDA records.[5]
  what is the definition of endoplasmic reticulum in biology	Endoplasmic reticulum The endoplasmic reticulum (ER) is a type of organelle in eukaryotic cells that forms an interconnected network of flattened, membrane-enclosed sacs or tube-like structures known as cisternae. The membranes of the ER are continuous with the outer nuclear membrane. The endoplasmic reticulum occurs in most types of eukaryotic cells, but is absent from red blood cells and spermatozoa. There are two types of endoplasmic reticulum: rough and smooth. The outer (cytosolic) face of the rough endoplasmic reticulum is studded with ribosomes that are the sites of protein synthesis. The rough endoplasmic reticulum is especially prominent in cells such as hepatocytes. The smooth endoplasmic reticulum lacks ribosomes and functions in lipid manufacture and metabolism, the production of steroid hormones, and detoxification.[1] The smooth ER is especially abundant in mammalian liver and gonad cells. The lacy membranes of the endoplasmic reticulum were first seen in 1945 using elect...
  what does the ski mean in polish names	Polish name Since the High Middle Ages, Polish-sounding surnames ending with the masculine -ski suffix, including -cki and -dzki, and the corresponding feminine suffix -ska/-cka/-dzka were associated with the nobility (Polish szlachta), which alone, in the early years, had such suffix distinctions.[1] They are widely popular today.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 4
  }
  

Evaluation Dataset

natural-questions

• Dataset: natural-questions at f9e894e
• Size: 1,000 evaluation samples
• Columns: query and answer
• Approximate statistics based on the first 1000 samples:

  	query	answer
  type	string	string
  details	min: 9 tokens mean: 11.62 tokens max: 23 tokens	min: 9 tokens mean: 141.66 tokens max: 664 tokens

• Samples:

  query	answer
  difference between russian blue and british blue cat	Russian Blue The coat is known as a "double coat", with the undercoat being soft, downy and equal in length to the guard hairs, which are an even blue with silver tips. However, the tail may have a few very dull, almost unnoticeable stripes. The coat is described as thick, plush and soft to the touch. The feeling is softer than the softest silk. The silver tips give the coat a shimmering appearance. Its eyes are almost always a dark and vivid green. Any white patches of fur or yellow eyes in adulthood are seen as flaws in show cats.[3] Russian Blues should not be confused with British Blues (which are not a distinct breed, but rather a British Shorthair with a blue coat as the British Shorthair breed itself comes in a wide variety of colors and patterns), nor the Chartreux or Korat which are two other naturally occurring breeds of blue cats, although they have similar traits.
  who played the little girl on mrs doubtfire	Mara Wilson Mara Elizabeth Wilson[2] (born July 24, 1987) is an American writer and former child actress. She is known for playing Natalie Hillard in Mrs. Doubtfire (1993), Susan Walker in Miracle on 34th Street (1994), Matilda Wormwood in Matilda (1996) and Lily Stone in Thomas and the Magic Railroad (2000). Since retiring from film acting, Wilson has focused on writing.
  what year did the movie the sound of music come out	The Sound of Music (film) The film was released on March 2, 1965 in the United States, initially as a limited roadshow theatrical release. Although critical response to the film was widely mixed, the film was a major commercial success, becoming the number one box office movie after four weeks, and the highest-grossing film of 1965. By November 1966, The Sound of Music had become the highest-grossing film of all-time—surpassing Gone with the Wind—and held that distinction for five years. The film was just as popular throughout the world, breaking previous box-office records in twenty-nine countries. Following an initial theatrical release that lasted four and a half years, and two successful re-releases, the film sold 283 million admissions worldwide and earned a total worldwide gross of $286,000,000.

• Loss: CachedMultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 4
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 12
• bf16: True
• prompts: {'query': 'query: ', 'answer': 'document: '}
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 1
• 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: 12
• 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
• hub_revision: None
• 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
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: {'query': 'query: ', 'answer': 'document: '}
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_cosine_ndcg@10	NanoNFCorpus_cosine_ndcg@10	NanoNQ_cosine_ndcg@10	NanoBEIR_mean_cosine_ndcg@10
-1	-1	-	-	0.0086	0.0233	0.0063	0.0128
0.0026	1	4.6189	-	-	-	-	-
0.0129	5	4.1284	-	-	-	-	-
0.0258	10	3.6638	-	-	-	-	-
0.0387	15	2.3118	-	-	-	-	-
0.0515	20	1.0986	-	-	-	-	-
0.0644	25	0.5063	-	-	-	-	-
0.0773	30	0.2891	-	-	-	-	-
0.0902	35	0.2138	-	-	-	-	-
0.1031	40	0.1967	-	-	-	-	-
0.1160	45	0.1745	-	-	-	-	-
0.1289	50	0.1479	0.1425	0.4927	0.3162	0.5375	0.4488
0.1418	55	0.1257	-	-	-	-	-
0.1546	60	0.1215	-	-	-	-	-
0.1675	65	0.1475	-	-	-	-	-
0.1804	70	0.1066	-	-	-	-	-
0.1933	75	0.1056	-	-	-	-	-
0.2062	80	0.1181	-	-	-	-	-
0.2191	85	0.118	-	-	-	-	-
0.2320	90	0.1031	-	-	-	-	-
0.2448	95	0.0775	-	-	-	-	-
0.2577	100	0.0906	0.1009	0.4791	0.3151	0.6007	0.4650
0.2706	105	0.0921	-	-	-	-	-
0.2835	110	0.1105	-	-	-	-	-
0.2964	115	0.0906	-	-	-	-	-
0.3093	120	0.1002	-	-	-	-	-
0.3222	125	0.0952	-	-	-	-	-
0.3351	130	0.0652	-	-	-	-	-
0.3479	135	0.079	-	-	-	-	-
0.3608	140	0.0951	-	-	-	-	-
0.3737	145	0.0918	-	-	-	-	-
0.3866	150	0.065	0.0772	0.5115	0.3070	0.6105	0.4763
0.3995	155	0.1065	-	-	-	-	-
0.4124	160	0.0871	-	-	-	-	-
0.4253	165	0.0623	-	-	-	-	-
0.4381	170	0.0771	-	-	-	-	-
0.4510	175	0.0795	-	-	-	-	-
0.4639	180	0.0814	-	-	-	-	-
0.4768	185	0.0794	-	-	-	-	-
0.4897	190	0.0744	-	-	-	-	-
0.5026	195	0.0612	-	-	-	-	-
0.5155	200	0.0684	0.0692	0.4818	0.3173	0.6161	0.4717
0.5284	205	0.0635	-	-	-	-	-
0.5412	210	0.0768	-	-	-	-	-
0.5541	215	0.0544	-	-	-	-	-
0.5670	220	0.0654	-	-	-	-	-
0.5799	225	0.0729	-	-	-	-	-
0.5928	230	0.0923	-	-	-	-	-
0.6057	235	0.0763	-	-	-	-	-
0.6186	240	0.0687	-	-	-	-	-
0.6314	245	0.0657	-	-	-	-	-
0.6443	250	0.0708	0.0643	0.4843	0.3152	0.6023	0.4673
0.6572	255	0.0555	-	-	-	-	-
0.6701	260	0.0792	-	-	-	-	-
0.6830	265	0.0681	-	-	-	-	-
0.6959	270	0.0855	-	-	-	-	-
0.7088	275	0.0788	-	-	-	-	-
0.7216	280	0.0631	-	-	-	-	-
0.7345	285	0.0676	-	-	-	-	-
0.7474	290	0.0536	-	-	-	-	-
0.7603	295	0.0814	-	-	-	-	-
0.7732	300	0.062	0.0606	0.4630	0.3235	0.6256	0.4707
0.7861	305	0.0777	-	-	-	-	-
0.7990	310	0.0801	-	-	-	-	-
0.8119	315	0.0566	-	-	-	-	-
0.8247	320	0.0711	-	-	-	-	-
0.8376	325	0.0643	-	-	-	-	-
0.8505	330	0.0422	-	-	-	-	-
0.8634	335	0.0614	-	-	-	-	-
0.8763	340	0.06	-	-	-	-	-
0.8892	345	0.0584	-	-	-	-	-
0.9021	350	0.0457	0.0583	0.4952	0.3214	0.6268	0.4811
0.9149	355	0.0838	-	-	-	-	-
0.9278	360	0.0657	-	-	-	-	-
0.9407	365	0.0658	-	-	-	-	-
0.9536	370	0.0757	-	-	-	-	-
0.9665	375	0.0603	-	-	-	-	-
0.9794	380	0.0647	-	-	-	-	-
0.9923	385	0.0575	-	-	-	-	-
-1	-1	-	-	0.4909	0.3236	0.6322	0.4822

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Energy Consumed: 1.043 kWh
• Carbon Emitted: 0.405 kg of CO2
• Hours Used: 3.425 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 5.1.0.dev0
• Transformers: 4.53.0
• PyTorch: 2.7.1+cu126
• Accelerate: 1.5.1
• Datasets: 2.21.0
• Tokenizers: 0.21.1

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",
}

CachedMultipleNegativesRankingLoss

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}