metadata

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:99000
  - loss:CSRLoss
base_model: microsoft/mpnet-base
widget:
  - source_sentence: what is the difference between uae and saudi arabia
    sentences:
      - >-
        Monopoly Junior Players take turns in order, with the initial player
        determined by age before the game: the youngest player goes first.
        Players are dealt an initial amount Monopoly money depending on the
        total number of players playing: 20 in a two-player game, 18 in a
        three-player game or 16 in a four-player game. A typical turn begins
        with the rolling of the die and the player advancing their token
        clockwise around the board the corresponding number of spaces. When the
        player lands on an unowned space they must purchase the space from the
        bank for the amount indicated on the board, and places a sold sign on
        the coloured band at the top of the space to denote ownership. If a
        player lands on a space owned by an opponent the player pays the
        opponent rent in the amount written on the board. If the opponent owns
        both properties of the same colour the rent is doubled.
      - >-
        Saudi Arabia–United Arab Emirates relations However, the UAE and Saudi
        Arabia continue to take somewhat differing stances on regional conflicts
        such the Yemeni Civil War, where the UAE opposes Al-Islah, and supports
        the Southern Movement, which has fought against Saudi-backed forces, and
        the Syrian Civil War, where the UAE has disagreed with Saudi support for
        Islamist movements.[4]
      - >-
        Governors of states of India The governors and lieutenant-governors are
        appointed by the President for a term of five years.
  - source_sentence: who came up with the seperation of powers
    sentences:
      - >-
        Separation of powers Aristotle first mentioned the idea of a "mixed
        government" or hybrid government in his work Politics where he drew upon
        many of the constitutional forms in the city-states of Ancient Greece.
        In the Roman Republic, the Roman Senate, Consuls and the Assemblies
        showed an example of a mixed government according to Polybius
        (Histories, Book 6, 11â€“13).
      - >-
        Economy of New Zealand New Zealand's diverse market economy has a
        sizable service sector, accounting for 63% of all GDP activity in
        2013.[17] Large scale manufacturing industries include aluminium
        production, food processing, metal fabrication, wood and paper products.
        Mining, manufacturing, electricity, gas, water, and waste services
        accounted for 16.5% of GDP in 2013.[17] The primary sector continues to
        dominate New Zealand's exports, despite accounting for 6.5% of GDP in
        2013.[17]
      - >-
        John Dalton John Dalton FRS (/ˈdɔːltən/; 6 September 1766 – 27 July
        1844) was an English chemist, physicist, and meteorologist. He is best
        known for proposing the modern atomic theory and for his research into
        colour blindness, sometimes referred to as Daltonism in his honour.
  - source_sentence: >-
      who was the first president of indian science congress meeting held in
      kolkata in 1914
    sentences:
      - >-
        Nobody to Blame "Nobody to Blame" is a song recorded by American country
        music artist Chris Stapleton. The song was released in November 2015 as
        the singer's third single overall. Stapleton co-wrote the song with
        Barry Bales and Ronnie Bowman. It became Stapleton's first top 10 single
        on the US Country Airplay chart.[2] "Nobody to Blame" won Song of the
        Year at the ACM Awards.[3]
      - >-
        Indian Science Congress Association The first meeting of the congress
        was held from 15â€“17 January 1914 at the premises of the Asiatic
        Society, Calcutta. Honorable justice Sir Ashutosh Mukherjee, the then
        Vice Chancellor of the University of Calcutta presided over the
        Congress. One hundred and five scientists from different parts of India
        and abroad attended it. Altogether 35 papers under 6 different sections,
        namely Botany, Chemistry, Ethnography, Geology, Physics and Zoology were
        presented.
      - >-
        New Soul "New Soul" is a song by the French-Israeli R&B/soul singer Yael
        Naïm, from her self-titled second album. The song gained popularity in
        the United States following its use by Apple in an advertisement for
        their MacBook Air laptop. In the song Naïm sings of being a new soul who
        has come into the world to learn "a bit 'bout how to give and take."
        However, she finds that things are harder than they seem. The song, also
        featured in the films The House Bunny and Wild Target, features a
        prominent "la la la la" section as its hook. It remains Naïm's biggest
        hit single in the U.S. to date, and her only one to reach the Top 40 of
        the Billboard Hot 100.
  - source_sentence: who wrote get over it by the eagles
    sentences:
      - >-
        Get Over It (Eagles song) "Get Over It" is a song by the Eagles released
        as a single after a fourteen-year breakup. It was also the first song
        written by bandmates Don Henley and Glenn Frey when the band reunited.
        "Get Over It" was played live for the first time during their Hell
        Freezes Over tour in 1994. It returned the band to the U.S. Top 40 after
        a fourteen-year absence, peaking at No. 31 on the Billboard Hot 100
        chart. It also hit No. 4 on the Billboard Mainstream Rock Tracks chart.
        The song was not played live by the Eagles after the "Hell Freezes Over"
        tour in 1994. It remains the group's last Top 40 hit in the U.S.
      - >-
        Pokhran-II In 1980, the general elections marked the return of Indira
        Gandhi and the nuclear program began to gain momentum under Ramanna in
        1981. Requests for additional nuclear tests were continued to be denied
        by the government when Prime Minister Indira Gandhi saw Pakistan began
        exercising the brinkmanship, though the nuclear program continued to
        advance.[7] Initiation towards hydrogen bomb began as well as the launch
        of the missile programme began under Late president Dr. Abdul Kalam, who
        was then an aerospace engineer.[7]
      - "R. Budd Dwyer Robert Budd Dwyer (November 21, 1939\_– January 22, 1987) was the 30th State Treasurer of the Commonwealth of Pennsylvania. He served from 1971 to 1981 as a Republican member of the Pennsylvania State Senate representing the state's 50th district. He then served as the 30th Treasurer of Pennsylvania from January 20, 1981, until his death. On January 22, 1987, Dwyer called a news conference in the Pennsylvania state capital of Harrisburg where he killed himself in front of the gathered reporters, by shooting himself in the mouth with a .357 Magnum revolver.[4] Dwyer's suicide was broadcast later that day to a wide television audience across Pennsylvania."
  - source_sentence: who is cornelius in the book of acts
    sentences:
      - >-
        Wonderful Tonight "Wonderful Tonight" is a ballad written by Eric
        Clapton. It was included on Clapton's 1977 album Slowhand. Clapton wrote
        the song about Pattie Boyd.[1] The female vocal harmonies on the song
        are provided by Marcella Detroit (then Marcy Levy) and Yvonne Elliman.
      - >-
        Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in
        1991 as their head of story.[1] There he worked on all of their films
        produced up to 2006; this included Toy Story (for which he received an
        Academy Award nomination) and A Bug's Life, as the co-story writer and
        others as story supervisor. His final film was Cars. He also voiced
        characters in many of the films, including Heimlich the caterpillar in A
        Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in
        Finding Nemo.[1]
      - >-
        Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman
        centurion who is considered by Christians to be one of the first
        Gentiles to convert to the faith, as related in Acts of the Apostles.
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: 113.44094173179047
  energy_consumed: 0.29184553136281904
  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: 0.773
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: SparseEncoder based on microsoft/mpnet-base
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 16
          type: NanoMSMARCO_16
        metrics:
          - type: cosine_accuracy@1
            value: 0.1
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.36
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.08666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05000000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.26
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.36
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.272077335852507
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.20234920634920633
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.21758364304569
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 16
          type: NanoNFCorpus_16
        metrics:
          - type: cosine_accuracy@1
            value: 0.08
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.14
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.24
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.32
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.05999999999999999
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.005993249911183041
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.009403252754209558
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.013285393478414642
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.01646720008819819
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.06095056479011788
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.14072222222222222
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.015310893897400863
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 16
          type: NanoNQ_16
        metrics:
          - type: cosine_accuracy@1
            value: 0.18
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.42
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.54
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.64
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.13999999999999999
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10800000000000003
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.064
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.4
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.5
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3867151912670764
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3266904761904762
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3250246379519026
            name: Cosine Map@100
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 16
          type: NanoBEIR_mean_16
        metrics:
          - type: cosine_accuracy@1
            value: 0.12
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.2733333333333334
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.38000000000000006
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.48666666666666664
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.12
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09555555555555555
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08666666666666668
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05466666666666667
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.09533108330372768
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2231344175847365
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.29109513115947155
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.3721557333627327
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2399143639699004
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.22325396825396826
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.18597305829833113
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 32
          type: NanoMSMARCO_32
        metrics:
          - type: cosine_accuracy@1
            value: 0.18
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.36
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.56
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.08666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05600000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.18
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.26
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.36
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.56
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.33109644128066057
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2634444444444444
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.27935469743863556
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 32
          type: NanoNFCorpus_32
        metrics:
          - type: cosine_accuracy@1
            value: 0.14
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.26
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.28
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.34
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.14
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09600000000000002
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.007695869325666863
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.012313937822266688
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.01702903494334016
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.024165659145052122
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.10225707780728845
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2055238095238095
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.022577551502700435
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 32
          type: NanoNQ_32
        metrics:
          - type: cosine_accuracy@1
            value: 0.32
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.46
            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: 0.32
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11600000000000002
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.068
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.31
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.42
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.53
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.63
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4603957123337682
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.4211904761904762
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.41127594932176303
            name: Cosine Map@100
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 32
          type: NanoBEIR_mean_32
        metrics:
          - type: cosine_accuracy@1
            value: 0.21333333333333335
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.32666666666666666
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4066666666666667
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5266666666666667
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.21333333333333335
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11777777777777776
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09466666666666668
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07133333333333335
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.16589862310855563
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.23077131260742223
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.30234301164778005
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4047218863816841
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.29791641047390577
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2967195767195767
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.23773606608769968
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 64
          type: NanoMSMARCO_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.16
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.38
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.46
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.16
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.12666666666666665
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.16
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.38
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.46
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3545165496884908
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.27796031746031746
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.29572845389453484
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 64
          type: NanoNFCorpus_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.18
            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: 0.4
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.12666666666666665
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.088
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.009483451025013268
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.012904129822135095
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.036867855927155205
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.04756198673273659
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.11496239522394665
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.24210317460317454
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.0318282871881163
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 64
          type: NanoNQ_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.44
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.62
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.68
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.72
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.44
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.20666666666666667
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.07400000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.42
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.58
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.64
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.68
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.561884513825323
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5395555555555555
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5268055680783221
            name: Cosine Map@100
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 64
          type: NanoBEIR_mean_64
        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: 0.48666666666666664
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5733333333333334
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.26
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15333333333333332
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11733333333333335
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.074
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.19649448367500444
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.32430137660737834
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3789559519757184
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4425206622442455
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3437878195792535
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.35320634920634914
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2847874363869911
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 128
          type: NanoMSMARCO_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.2
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.34
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.46
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.68
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.2
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09200000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.068
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.2
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.34
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.46
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.68
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4022072447482653
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.31815873015873014
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.33230553462724927
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 128
          type: NanoNFCorpus_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.14
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.34
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.38
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.52
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.14
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.16666666666666663
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.128
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.11399999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.0036955722371344803
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.021194355136532755
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.024553995602026958
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.043293677887263404
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.12666378888376595
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2537936507936508
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.03330968914510828
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 128
          type: NanoNQ_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.38
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.56
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.38
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.18666666666666665
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14400000000000002
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08199999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.35
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.53
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.66
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.76
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5527057053472701
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5072460317460317
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.4846991157483792
            name: Cosine Map@100
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 128
          type: NanoBEIR_mean_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.24
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4133333333333334
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5133333333333333
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6666666666666666
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.24
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15555555555555553
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12133333333333335
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08800000000000001
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1845651907457115
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.2970647850455109
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.381517998534009
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4944312259624211
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3605255796597671
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.35973280423280424
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2834381131735789
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 256
          type: NanoMSMARCO_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.26
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.48
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.52
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.68
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.26
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.15999999999999998
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.10400000000000001
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.068
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.26
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.48
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.52
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.68
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4651758219790261
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.39804761904761904
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.412474140043243
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 256
          type: NanoNFCorpus_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.18
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.28
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.38
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.18
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.14666666666666667
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.114
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.005516710448516594
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.011401609103753301
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.021271103372355084
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.0347182833647384
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.12628863554710404
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2575
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.033728487141126466
            name: Cosine Map@100
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 256
          type: NanoNQ_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.42
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.58
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.68
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.76
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.42
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.19333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.4
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.54
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.64
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.73
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5611650669716552
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5226904761904763
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5086922580864135
            name: Cosine Map@100
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 256
          type: NanoBEIR_mean_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.2866666666666667
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.4466666666666666
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.5266666666666667
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6466666666666667
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.2866666666666667
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.16666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.128
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08733333333333333
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.22183890348283888
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3438005363679178
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3937570344574517
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.48157276112157943
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3842098414992618
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3927460317460318
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.31829829509026103
            name: Cosine Map@100

SparseEncoder based on microsoft/mpnet-base

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the natural-questions dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

See train_nq.py for the training script used for this model.

Warning: Sparse models in Sentence Transformers are still quite experimental.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: microsoft/mpnet-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- natural-questions
Language: en

Model Sources

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

Full Model Architecture

SparseEncoder(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): CSRSparsity({'input_dim': 768, 'hidden_dim': 3072, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30})
)

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/sparse-mpnet-base-nq-fresh")
# Run inference
sentences = [
    'who is cornelius in the book of acts',
    'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.',
    "Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in 1991 as their head of story.[1] There he worked on all of their films produced up to 2006; this included Toy Story (for which he received an Academy Award nomination) and A Bug's Life, as the co-story writer and others as story supervisor. His final film was Cars. He also voiced characters in many of the films, including Heimlich the caterpillar in A Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in Finding Nemo.[1]",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Sparse Information Retrieval

Datasets: NanoMSMARCO_16, NanoNFCorpus_16 and NanoNQ_16
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 16
}
```

Metric	NanoMSMARCO_16	NanoNFCorpus_16	NanoNQ_16
cosine_accuracy@1	0.1	0.08	0.18
cosine_accuracy@3	0.26	0.14	0.42
cosine_accuracy@5	0.36	0.24	0.54
cosine_accuracy@10	0.5	0.32	0.64
cosine_precision@1	0.1	0.08	0.18
cosine_precision@3	0.0867	0.06	0.14
cosine_precision@5	0.072	0.08	0.108
cosine_precision@10	0.05	0.05	0.064
cosine_recall@1	0.1	0.006	0.18
cosine_recall@3	0.26	0.0094	0.4
cosine_recall@5	0.36	0.0133	0.5
cosine_recall@10	0.5	0.0165	0.6
cosine_ndcg@10	0.2721	0.061	0.3867
cosine_mrr@10	0.2023	0.1407	0.3267
cosine_map@100	0.2176	0.0153	0.325

Sparse Nano BEIR

Dataset: NanoBEIR_mean_16

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "truncate_dim": 16
}

Metric	Value
cosine_accuracy@1	0.12
cosine_accuracy@3	0.2733
cosine_accuracy@5	0.38
cosine_accuracy@10	0.4867
cosine_precision@1	0.12
cosine_precision@3	0.0956
cosine_precision@5	0.0867
cosine_precision@10	0.0547
cosine_recall@1	0.0953
cosine_recall@3	0.2231
cosine_recall@5	0.2911
cosine_recall@10	0.3722
cosine_ndcg@10	0.2399
cosine_mrr@10	0.2233
cosine_map@100	0.186

Sparse Information Retrieval

Datasets: NanoMSMARCO_32, NanoNFCorpus_32 and NanoNQ_32
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 32
}
```

Metric	NanoMSMARCO_32	NanoNFCorpus_32	NanoNQ_32
cosine_accuracy@1	0.18	0.14	0.32
cosine_accuracy@3	0.26	0.26	0.46
cosine_accuracy@5	0.36	0.28	0.58
cosine_accuracy@10	0.56	0.34	0.68
cosine_precision@1	0.18	0.14	0.32
cosine_precision@3	0.0867	0.1133	0.1533
cosine_precision@5	0.072	0.096	0.116
cosine_precision@10	0.056	0.09	0.068
cosine_recall@1	0.18	0.0077	0.31
cosine_recall@3	0.26	0.0123	0.42
cosine_recall@5	0.36	0.017	0.53
cosine_recall@10	0.56	0.0242	0.63
cosine_ndcg@10	0.3311	0.1023	0.4604
cosine_mrr@10	0.2634	0.2055	0.4212
cosine_map@100	0.2794	0.0226	0.4113

Sparse Nano BEIR

Dataset: NanoBEIR_mean_32

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "truncate_dim": 32
}

Metric	Value
cosine_accuracy@1	0.2133
cosine_accuracy@3	0.3267
cosine_accuracy@5	0.4067
cosine_accuracy@10	0.5267
cosine_precision@1	0.2133
cosine_precision@3	0.1178
cosine_precision@5	0.0947
cosine_precision@10	0.0713
cosine_recall@1	0.1659
cosine_recall@3	0.2308
cosine_recall@5	0.3023
cosine_recall@10	0.4047
cosine_ndcg@10	0.2979
cosine_mrr@10	0.2967
cosine_map@100	0.2377

Sparse Information Retrieval

Datasets: NanoMSMARCO_64, NanoNFCorpus_64 and NanoNQ_64
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	NanoMSMARCO_64	NanoNFCorpus_64	NanoNQ_64
cosine_accuracy@1	0.16	0.18	0.44
cosine_accuracy@3	0.38	0.26	0.62
cosine_accuracy@5	0.46	0.32	0.68
cosine_accuracy@10	0.6	0.4	0.72
cosine_precision@1	0.16	0.18	0.44
cosine_precision@3	0.1267	0.1267	0.2067
cosine_precision@5	0.092	0.12	0.14
cosine_precision@10	0.06	0.088	0.074
cosine_recall@1	0.16	0.0095	0.42
cosine_recall@3	0.38	0.0129	0.58
cosine_recall@5	0.46	0.0369	0.64
cosine_recall@10	0.6	0.0476	0.68
cosine_ndcg@10	0.3545	0.115	0.5619
cosine_mrr@10	0.278	0.2421	0.5396
cosine_map@100	0.2957	0.0318	0.5268

Sparse Nano BEIR

Dataset: NanoBEIR_mean_64

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "truncate_dim": 64
}

Metric	Value
cosine_accuracy@1	0.26
cosine_accuracy@3	0.42
cosine_accuracy@5	0.4867
cosine_accuracy@10	0.5733
cosine_precision@1	0.26
cosine_precision@3	0.1533
cosine_precision@5	0.1173
cosine_precision@10	0.074
cosine_recall@1	0.1965
cosine_recall@3	0.3243
cosine_recall@5	0.379
cosine_recall@10	0.4425
cosine_ndcg@10	0.3438
cosine_mrr@10	0.3532
cosine_map@100	0.2848

Sparse Information Retrieval

Datasets: NanoMSMARCO_128, NanoNFCorpus_128 and NanoNQ_128
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 128
}
```

Metric	NanoMSMARCO_128	NanoNFCorpus_128	NanoNQ_128
cosine_accuracy@1	0.2	0.14	0.38
cosine_accuracy@3	0.34	0.34	0.56
cosine_accuracy@5	0.46	0.38	0.7
cosine_accuracy@10	0.68	0.52	0.8
cosine_precision@1	0.2	0.14	0.38
cosine_precision@3	0.1133	0.1667	0.1867
cosine_precision@5	0.092	0.128	0.144
cosine_precision@10	0.068	0.114	0.082
cosine_recall@1	0.2	0.0037	0.35
cosine_recall@3	0.34	0.0212	0.53
cosine_recall@5	0.46	0.0246	0.66
cosine_recall@10	0.68	0.0433	0.76
cosine_ndcg@10	0.4022	0.1267	0.5527
cosine_mrr@10	0.3182	0.2538	0.5072
cosine_map@100	0.3323	0.0333	0.4847

Sparse Nano BEIR

Dataset: NanoBEIR_mean_128

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "truncate_dim": 128
}

Metric	Value
cosine_accuracy@1	0.24
cosine_accuracy@3	0.4133
cosine_accuracy@5	0.5133
cosine_accuracy@10	0.6667
cosine_precision@1	0.24
cosine_precision@3	0.1556
cosine_precision@5	0.1213
cosine_precision@10	0.088
cosine_recall@1	0.1846
cosine_recall@3	0.2971
cosine_recall@5	0.3815
cosine_recall@10	0.4944
cosine_ndcg@10	0.3605
cosine_mrr@10	0.3597
cosine_map@100	0.2834

Sparse Information Retrieval

Datasets: NanoMSMARCO_256, NanoNFCorpus_256 and NanoNQ_256
Evaluated with SparseInformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	NanoMSMARCO_256	NanoNFCorpus_256	NanoNQ_256
cosine_accuracy@1	0.26	0.18	0.42
cosine_accuracy@3	0.48	0.28	0.58
cosine_accuracy@5	0.52	0.38	0.68
cosine_accuracy@10	0.68	0.5	0.76
cosine_precision@1	0.26	0.18	0.42
cosine_precision@3	0.16	0.1467	0.1933
cosine_precision@5	0.104	0.14	0.14
cosine_precision@10	0.068	0.114	0.08
cosine_recall@1	0.26	0.0055	0.4
cosine_recall@3	0.48	0.0114	0.54
cosine_recall@5	0.52	0.0213	0.64
cosine_recall@10	0.68	0.0347	0.73
cosine_ndcg@10	0.4652	0.1263	0.5612
cosine_mrr@10	0.398	0.2575	0.5227
cosine_map@100	0.4125	0.0337	0.5087

Sparse Nano BEIR

Dataset: NanoBEIR_mean_256

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ],
    "truncate_dim": 256
}

Metric	Value
cosine_accuracy@1	0.2867
cosine_accuracy@3	0.4467
cosine_accuracy@5	0.5267
cosine_accuracy@10	0.6467
cosine_precision@1	0.2867
cosine_precision@3	0.1667
cosine_precision@5	0.128
cosine_precision@10	0.0873
cosine_recall@1	0.2218
cosine_recall@3	0.3438
cosine_recall@5	0.3938
cosine_recall@10	0.4816
cosine_ndcg@10	0.3842
cosine_mrr@10	0.3927
cosine_map@100	0.3183

Training Details

Training Dataset

natural-questions

Dataset: natural-questions at f9e894e
Size: 99,000 training samples
Columns: query and answer
Approximate statistics based on the first 1000 samples:
query answer
type string string
details
min: 10 tokens
mean: 11.71 tokens
max: 26 tokens

min: 4 tokens
mean: 131.81 tokens
max: 450 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 11.71 tokens max: 26 tokens	min: 4 tokens mean: 131.81 tokens max: 450 tokens

Samples:

query	answer
`who played the father in papa don't preach`	`Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.`
`where was the location of the battle of hastings`	`Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.`
`how many puppies can a dog give birth to`	`Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]`

Loss: CSRLoss with these parameters:

{
    "beta": 0.1,
    "gamma": 1,
    "scale": 20.0
}

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: 10 tokens
mean: 11.69 tokens
max: 23 tokens

min: 15 tokens
mean: 134.01 tokens
max: 512 tokens

	query	answer
type	string	string
details	min: 10 tokens mean: 11.69 tokens max: 23 tokens	min: 15 tokens mean: 134.01 tokens max: 512 tokens

Samples:

query	answer
`where is the tiber river located in italy`	Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.
`what kind of car does jay gatsby drive`	`Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.`
`who sings if i can dream about you`	`I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]`

Loss: CSRLoss with these parameters:

{
    "beta": 0.1,
    "gamma": 1,
    "scale": 20.0
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 4e-05
weight_decay: 0.0001
adam_epsilon: 6.25e-10
num_train_epochs: 1
warmup_ratio: 0.1
bf16: True
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: 32
per_device_eval_batch_size: 32
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: 4e-05
weight_decay: 0.0001
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 6.25e-10
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: 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}
tp_size: 0
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
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_16_cosine_ndcg@10	NanoNFCorpus_16_cosine_ndcg@10	NanoNQ_16_cosine_ndcg@10	NanoBEIR_mean_16_cosine_ndcg@10	NanoMSMARCO_32_cosine_ndcg@10	NanoNFCorpus_32_cosine_ndcg@10	NanoNQ_32_cosine_ndcg@10	NanoBEIR_mean_32_cosine_ndcg@10	NanoMSMARCO_64_cosine_ndcg@10	NanoNFCorpus_64_cosine_ndcg@10	NanoNQ_64_cosine_ndcg@10	NanoBEIR_mean_64_cosine_ndcg@10	NanoMSMARCO_128_cosine_ndcg@10	NanoNFCorpus_128_cosine_ndcg@10	NanoNQ_128_cosine_ndcg@10	NanoBEIR_mean_128_cosine_ndcg@10	NanoMSMARCO_256_cosine_ndcg@10	NanoNFCorpus_256_cosine_ndcg@10	NanoNQ_256_cosine_ndcg@10	NanoBEIR_mean_256_cosine_ndcg@10
-1	-1	-	-	0.0318	0.0148	0.0149	0.0205	0.0794	0.0234	0.0102	0.0377	0.0855	0.0195	0.0508	0.0519	0.1081	0.0246	0.0264	0.0530	0.1006	0.0249	0.0388	0.0547
0.0646	200	0.7332	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	400	0.2606	0.1970	0.2845	0.0970	0.3546	0.2454	0.3778	0.1358	0.3455	0.2864	0.3868	0.1563	0.3806	0.3079	0.3988	0.1664	0.4035	0.3229	0.4020	0.1782	0.4181	0.3327
0.1939	600	0.2247	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	800	0.1983	0.1750	0.2908	0.0866	0.3730	0.2502	0.3324	0.1155	0.4275	0.2918	0.3511	0.1621	0.4998	0.3377	0.3920	0.1563	0.5174	0.3553	0.4152	0.1555	0.5153	0.3620
0.3232	1000	0.1822	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	1200	0.1846	0.1594	0.2775	0.0785	0.3723	0.2428	0.2642	0.1076	0.4389	0.2702	0.3865	0.1328	0.4329	0.3174	0.3883	0.1446	0.5040	0.3456	0.3638	0.1529	0.4939	0.3369
0.4525	1400	0.1669	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	1600	0.1573	0.1452	0.2740	0.0624	0.3670	0.2345	0.3557	0.0855	0.4188	0.2867	0.4094	0.1099	0.5027	0.3407	0.3885	0.1340	0.4990	0.3405	0.4820	0.1577	0.5453	0.3950
0.5818	1800	0.1502	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	2000	0.1375	0.1255	0.2307	0.0685	0.3801	0.2264	0.2529	0.0815	0.4335	0.2560	0.3509	0.0955	0.4611	0.3025	0.3932	0.1339	0.4875	0.3382	0.4184	0.1483	0.4904	0.3523
0.7111	2200	0.1359	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	2400	0.1288	0.1184	0.2737	0.0703	0.3419	0.2286	0.3765	0.0843	0.4440	0.3016	0.3927	0.1247	0.5285	0.3486	0.3726	0.1203	0.5153	0.3361	0.4676	0.1343	0.5523	0.3847
0.8403	2600	0.1235	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	2800	0.1168	0.1094	0.2751	0.0710	0.3602	0.2354	0.3227	0.0966	0.5046	0.3080	0.4112	0.1129	0.5268	0.3503	0.4077	0.1259	0.5253	0.3530	0.4642	0.1238	0.5726	0.3869
0.9696	3000	0.1187	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.2721	0.0610	0.3867	0.2399	0.3311	0.1023	0.4604	0.2979	0.3545	0.1150	0.5619	0.3438	0.4022	0.1267	0.5527	0.3605	0.4652	0.1263	0.5612	0.3842

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.292 kWh
Carbon Emitted: 0.113 kg of CO2
Hours Used: 0.773 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: 4.1.0.dev0
Transformers: 4.52.0.dev0
PyTorch: 2.6.0+cu124
Accelerate: 1.5.1
Datasets: 3.3.2
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",
}