metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:99000
  - loss:SpladeLoss
  - loss:SparseMultipleNegativesRankingLoss
  - loss:FlopsLoss
base_model: distilbert/distilbert-base-uncased
widget:
  - text: >-
      Rollin' (Limp Bizkit song) The music video was filmed atop the South Tower
      of the former World Trade Center in New York City. The introduction
      features Ben Stiller and Stephen Dorff mistaking Fred Durst for the valet
      and giving him the keys to their Bentley Azure. Also making a cameo is
      break dancer Mr. Wiggles. The rest of the video has several cuts to Durst
      and his bandmates hanging out of the Bentley as they drive about
      Manhattan. The song Ben Stiller is playing at the beginning is "My
      Generation" from the same album. The video also features scenes of Fred
      Durst with five girls dancing in a room. The video was filmed around the
      same time as the film Zoolander, which explains Stiller and Dorff's
      appearance. Fred Durst has a small cameo in that film.
  - text: >-
      Maze Runner: The Death Cure On April 22, 2017, the studio delayed the
      release date once again, to February 9, 2018, in order to allow more time
      for post-production; months later, on August 25, the studio moved the
      release forward two weeks.[17] The film will premiere on January 26, 2018
      in 3D, IMAX and IMAX 3D.[18][19]
  - text: who played the dj in the movie the warriors
  - text: >-
      Lionel Messi Born and raised in central Argentina, Messi was diagnosed
      with a growth hormone deficiency as a child. At age 13, he relocated to
      Spain to join Barcelona, who agreed to pay for his medical treatment.
      After a fast progression through Barcelona's youth academy, Messi made his
      competitive debut aged 17 in October 2004. Despite being injury-prone
      during his early career, he established himself as an integral player for
      the club within the next three years, finishing 2007 as a finalist for
      both the Ballon d'Or and FIFA World Player of the Year award, a feat he
      repeated the following year. His first uninterrupted campaign came in the
      2008â€“09 season, during which he helped Barcelona achieve the first
      treble in Spanish football. At 22 years old, Messi won the Ballon d'Or and
      FIFA World Player of the Year award by record voting margins.
  - text: >-
      Send In the Clowns "Send In the Clowns" is a song written by Stephen
      Sondheim for the 1973 musical A Little Night Music, an adaptation of
      Ingmar Bergman's film Smiles of a Summer Night. It is a ballad from Act
      Two, in which the character Desirée reflects on the ironies and
      disappointments of her life. Among other things, she looks back on an
      affair years earlier with the lawyer Fredrik, who was deeply in love with
      her but whose marriage proposals she had rejected. Meeting him after so
      long, she realizes she is in love with him and finally ready to marry him,
      but now it is he who rejects her: he is in an unconsummated marriage with
      a much younger woman. Desirée proposes marriage to rescue him from this
      situation, but he declines, citing his dedication to his bride. Reacting
      to his rejection, Desirée sings this song. The song is later reprised as a
      coda after Fredrik's young wife runs away with his son, and Fredrik is
      finally free to accept Desirée's offer.[1]
datasets:
  - sentence-transformers/natural-questions
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
  - query_active_dims
  - query_sparsity_ratio
  - corpus_active_dims
  - corpus_sparsity_ratio
co2_eq_emissions:
  emissions: 32.40901449048007
  energy_consumed: 0.08337753469362151
  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: 0.285
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: splade-distilbert-base-uncased trained on Natural Questions
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.12000000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.28
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.52
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.6
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.74
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4954197868237354
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.41905555555555546
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.43020916049077634
            name: Dot Map@100
          - type: query_active_dims
            value: 62.65999984741211
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9979470545885784
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 110.4578628540039
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9963810411226655
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.26
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.26
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16666666666666669
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.128
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.26
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.64
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.74
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4944666703438861
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.41657936507936505
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.42694690636460897
            name: Dot Map@100
          - type: query_active_dims
            value: 70.22000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9976993643529027
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 125.49811553955078
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9958882735227197
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.44
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.46
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.52
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.272
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.22399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01892455420216294
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.04889990251243477
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.0672946061870769
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.08887922550901164
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.26311322734975795
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3882460317460318
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.11155968685488596
            name: Dot Map@100
          - type: query_active_dims
            value: 74.22000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9975683113419598
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 152.51846313476562
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9950029990454503
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.48
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.58
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.31999999999999995
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.264
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.23200000000000004
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01967175630881205
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.04958955768484856
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.06588472678704523
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.08890872761034473
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2726981353115194
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.42394444444444446
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.11062543949876841
            name: Dot Map@100
          - type: query_active_dims
            value: 85.58000183105469
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971961207708848
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 182.97967529296875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9940049906528744
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.34
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.56
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.64
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.66
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5163228308253419
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.48788888888888876
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4744598045833104
            name: Dot Map@100
          - type: query_active_dims
            value: 46.939998626708984
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984620929615783
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 96.43376159667969
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9968405162965507
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.35
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.55
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.65
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.66
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5211787059288393
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.49649999999999994
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.48018058391724333
            name: Dot Map@100
          - type: query_active_dims
            value: 55.08000183105469
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9981953999793246
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 114.79106140136719
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9962390714435041
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean
          type: NanoBEIR_mean
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5800000000000001
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6533333333333333
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22888888888888884
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17600000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.12266666666666666
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.212974851400721
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.37629996750414496
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.43576486872902565
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4962930751696706
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.42495194833294514
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4317301587301587
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.33874288397632424
            name: Dot Map@100
          - type: query_active_dims
            value: 61.27333323160807
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9979924862973721
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 119.80336252848308
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9960748521548889
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.4594348508634223
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6475039246467816
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7245525902668759
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7984615384615383
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4594348508634223
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.29682888540031394
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.23129042386185245
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1639026687598116
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2607784592309238
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.41707679910314266
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4815762664814047
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5608540436995575
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5109231200022869
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5709977698038922
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4325529585492243
            name: Dot Map@100
          - type: query_active_dims
            value: 86.22103676429161
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971751183813548
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 137.4154827411358
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9954978218091496
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.26
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.36
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.48
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.58
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.26
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.13333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10800000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.074
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.12833333333333333
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.18833333333333332
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.24666666666666665
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.30333333333333334
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2564995235608964
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3453015873015872
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2062826189577625
            name: Dot Map@100
          - type: query_active_dims
            value: 86.26000213623047
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971738417490259
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 128.0489959716797
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9958046983824231
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.62
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.84
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.92
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.62
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.54
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.49200000000000005
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.43400000000000005
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08260659025654458
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.14565005878146683
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1854201572717294
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2804326420122478
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.534178112145825
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7352222222222222
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.41480896090579994
            name: Dot Map@100
          - type: query_active_dims
            value: 55.939998626708984
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9981672236869567
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 125.40165710449219
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9958914338148059
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.64
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.84
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.98
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.64
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2866666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.18799999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.6166666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8166666666666668
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8766666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9433333333333332
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7890721601412974
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7516904761904764
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.7337194522253345
            name: Dot Map@100
          - type: query_active_dims
            value: 84.86000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9972197103528487
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 142.34327697753906
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9953363712411526
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.24
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.44
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.52
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.66
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.24
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16666666666666669
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.128
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09199999999999997
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.13585714285714284
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.28919047619047616
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.33274603174603173
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4233015873015873
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.32546154855128656
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3704365079365079
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.26492479686181064
            name: Dot Map@100
          - type: query_active_dims
            value: 65.44000244140625
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9978559726609854
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 132.02734375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9956743547686915
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.74
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.94
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.74
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.41999999999999993
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.27599999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.156
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.37
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.63
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.69
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.78
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7118024522387334
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8268888888888888
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6307915421731377
            name: Dot Map@100
          - type: query_active_dims
            value: 81.9000015258789
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9973166895509509
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 142.991943359375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9953151188205434
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.86
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.94
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.98
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.86
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.24799999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.132
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7706666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8846666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9359999999999999
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9733333333333333
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.909591417031897
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.904190476190476
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8825369408369409
            name: Dot Map@100
          - type: query_active_dims
            value: 58.36000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9980879365503456
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 64.70333099365234
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9978801084138113
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.28
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.236
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.16799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.086
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.17566666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.24466666666666664
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3446666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3317925768694159
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.533222222222222
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.25209583120462153
            name: Dot Map@100
          - type: query_active_dims
            value: 134.1999969482422
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9956031715828503
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 164.88478088378906
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9945978382516287
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.1
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.1
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.12400000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.52
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.62
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.44172833183312293
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.32852380952380955
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3339302930314127
            name: Dot Map@100
          - type: query_active_dims
            value: 152.0399932861328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9950186752740275
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 149.56478881835938
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9950997710235777
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.46
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.425
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.545
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.59
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.67
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5519450641329704
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5232698412698412
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5187507919958133
            name: Dot Map@100
          - type: query_active_dims
            value: 138.32000732421875
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9954681866416284
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 166.03871154785156
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9945600317296425
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.6326530612244898
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8775510204081632
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9591836734693877
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6326530612244898
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6054421768707483
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5387755102040817
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.43673469387755104
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04531781391284345
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.12723496235073023
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.18244054845345592
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2837929445033988
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5015858619400403
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.767201166180758
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3675943031666616
            name: Dot Map@100
          - type: query_active_dims
            value: 52.67346954345703
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982742458048799
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 147.12759399414062
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9951796214535699
            name: Corpus Sparsity Ratio

splade-distilbert-base-uncased trained on Natural Questions

This is a SPLADE Sparse Encoder model finetuned from distilbert/distilbert-base-uncased on the natural-questions dataset using the sentence-transformers library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: SPLADE Sparse Encoder
Base model: distilbert/distilbert-base-uncased
Maximum Sequence Length: 256 tokens
Output Dimensionality: 30522 dimensions
Similarity Function: Dot Product
Training Dataset:
- natural-questions
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Sparse Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sparse Encoders on Hugging Face

Full Model Architecture

SparseEncoder(
  (0): MLMTransformer({'max_seq_length': 256, 'do_lower_case': False}) with MLMTransformer model: DistilBertForMaskedLM 
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

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 SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/splade-distilbert-base-uncased-nq-updated-sparsity")
# Run inference
sentences = [
    'is send in the clowns from a musical',
    'Send In the Clowns "Send In the Clowns" is a song written by Stephen Sondheim for the 1973 musical A Little Night Music, an adaptation of Ingmar Bergman\'s film Smiles of a Summer Night. It is a ballad from Act Two, in which the character Desirée reflects on the ironies and disappointments of her life. Among other things, she looks back on an affair years earlier with the lawyer Fredrik, who was deeply in love with her but whose marriage proposals she had rejected. Meeting him after so long, she realizes she is in love with him and finally ready to marry him, but now it is he who rejects her: he is in an unconsummated marriage with a much younger woman. Desirée proposes marriage to rescue him from this situation, but he declines, citing his dedication to his bride. Reacting to his rejection, Desirée sings this song. The song is later reprised as a coda after Fredrik\'s young wife runs away with his son, and Fredrik is finally free to accept Desirée\'s offer.[1]',
    'The Suite Life on Deck The Suite Life on Deck is an American sitcom that aired on Disney Channel from September 26, 2008 to May 6, 2011. It is a sequel/spin-off of the Disney Channel Original Series The Suite Life of Zack & Cody. The series follows twin brothers Zack and Cody Martin and hotel heiress London Tipton in a new setting, the SS Tipton, where they attend classes at "Seven Seas High School" and meet Bailey Pickett while Mr. Moseby manages the ship. The ship travels around the world to nations such as Italy, France, Greece, India, Sweden and the United Kingdom where the characters experience different cultures, adventures, and situations.[1]',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 30522)

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

Evaluation

Metrics

Sparse Information Retrieval

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

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
dot_accuracy@1	0.26	0.36	0.38	0.26	0.62	0.64	0.24	0.74	0.86	0.42	0.1	0.46	0.6327
dot_accuracy@3	0.5	0.46	0.58	0.36	0.84	0.84	0.44	0.9	0.94	0.6	0.52	0.56	0.8776
dot_accuracy@5	0.64	0.48	0.68	0.48	0.9	0.9	0.52	0.94	0.98	0.72	0.62	0.6	0.9592
dot_accuracy@10	0.74	0.58	0.7	0.58	0.92	0.98	0.66	0.96	1.0	0.78	0.8	0.68	1.0
dot_precision@1	0.26	0.36	0.38	0.26	0.62	0.64	0.24	0.74	0.86	0.42	0.1	0.46	0.6327
dot_precision@3	0.1667	0.32	0.1933	0.1333	0.54	0.2867	0.1667	0.42	0.3667	0.28	0.1733	0.2067	0.6054
dot_precision@5	0.128	0.264	0.136	0.108	0.492	0.188	0.128	0.276	0.248	0.236	0.124	0.14	0.5388
dot_precision@10	0.074	0.232	0.07	0.074	0.434	0.104	0.092	0.156	0.132	0.168	0.08	0.078	0.4367
dot_recall@1	0.26	0.0197	0.35	0.1283	0.0826	0.6167	0.1359	0.37	0.7707	0.086	0.1	0.425	0.0453
dot_recall@3	0.5	0.0496	0.55	0.1883	0.1457	0.8167	0.2892	0.63	0.8847	0.1757	0.52	0.545	0.1272
dot_recall@5	0.64	0.0659	0.65	0.2467	0.1854	0.8767	0.3327	0.69	0.936	0.2447	0.62	0.59	0.1824
dot_recall@10	0.74	0.0889	0.66	0.3033	0.2804	0.9433	0.4233	0.78	0.9733	0.3447	0.8	0.67	0.2838
dot_ndcg@10	0.4945	0.2727	0.5212	0.2565	0.5342	0.7891	0.3255	0.7118	0.9096	0.3318	0.4417	0.5519	0.5016
dot_mrr@10	0.4166	0.4239	0.4965	0.3453	0.7352	0.7517	0.3704	0.8269	0.9042	0.5332	0.3285	0.5233	0.7672
dot_map@100	0.4269	0.1106	0.4802	0.2063	0.4148	0.7337	0.2649	0.6308	0.8825	0.2521	0.3339	0.5188	0.3676
query_active_dims	70.22	85.58	55.08	86.26	55.94	84.86	65.44	81.9	58.36	134.2	152.04	138.32	52.6735
query_sparsity_ratio	0.9977	0.9972	0.9982	0.9972	0.9982	0.9972	0.9979	0.9973	0.9981	0.9956	0.995	0.9955	0.9983
corpus_active_dims	125.4981	182.9797	114.7911	128.049	125.4017	142.3433	132.0273	142.9919	64.7033	164.8848	149.5648	166.0387	147.1276
corpus_sparsity_ratio	0.9959	0.994	0.9962	0.9958	0.9959	0.9953	0.9957	0.9953	0.9979	0.9946	0.9951	0.9946	0.9952

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.32
dot_accuracy@3	0.52
dot_accuracy@5	0.58
dot_accuracy@10	0.6533
dot_precision@1	0.32
dot_precision@3	0.2289
dot_precision@5	0.176
dot_precision@10	0.1227
dot_recall@1	0.213
dot_recall@3	0.3763
dot_recall@5	0.4358
dot_recall@10	0.4963
dot_ndcg@10	0.425
dot_mrr@10	0.4317
dot_map@100	0.3387
query_active_dims	61.2733
query_sparsity_ratio	0.998
corpus_active_dims	119.8034
corpus_sparsity_ratio	0.9961

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

{
    "dataset_names": [
        "climatefever",
        "dbpedia",
        "fever",
        "fiqa2018",
        "hotpotqa",
        "msmarco",
        "nfcorpus",
        "nq",
        "quoraretrieval",
        "scidocs",
        "arguana",
        "scifact",
        "touche2020"
    ]
}

Metric	Value
dot_accuracy@1	0.4594
dot_accuracy@3	0.6475
dot_accuracy@5	0.7246
dot_accuracy@10	0.7985
dot_precision@1	0.4594
dot_precision@3	0.2968
dot_precision@5	0.2313
dot_precision@10	0.1639
dot_recall@1	0.2608
dot_recall@3	0.4171
dot_recall@5	0.4816
dot_recall@10	0.5609
dot_ndcg@10	0.5109
dot_mrr@10	0.571
dot_map@100	0.4326
query_active_dims	86.221
query_sparsity_ratio	0.9972
corpus_active_dims	137.4155
corpus_sparsity_ratio	0.9955

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: SpladeLoss with these parameters:

{
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
    "lambda_corpus": 3e-05,
    "lambda_query": 5e-05
}

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: SpladeLoss with these parameters:

{
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
    "lambda_corpus": 3e-05,
    "lambda_query": 5e-05
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 12
per_device_eval_batch_size: 12
learning_rate: 2e-05
num_train_epochs: 1
bf16: True
load_best_model_at_end: 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: 12
per_device_eval_batch_size: 12
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: 0.0
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: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10
0.0242	200	4.7655	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0485	400	0.168	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0727	600	0.0672	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0970	800	0.0533	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1212	1000	0.0605	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1455	1200	0.051	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1697	1400	0.0244	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	1600	0.0306	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2	1650	-	0.0220	0.4946	0.2654	0.4801	0.4134	-	-	-	-	-	-	-	-	-	-
0.2182	1800	0.0246	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2424	2000	0.0445	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2667	2200	0.0322	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2909	2400	0.0316	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3152	2600	0.029	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3394	2800	0.0145	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3636	3000	0.0312	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3879	3200	0.0232	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4	3300	-	0.0155	0.4420	0.2753	0.5112	0.4095	-	-	-	-	-	-	-	-	-	-
0.4121	3400	0.0245	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4364	3600	0.0233	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4606	3800	0.0224	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4848	4000	0.0126	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5091	4200	0.0269	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5333	4400	0.0245	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5576	4600	0.0214	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	4800	0.0276	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6	4950	-	0.0098	0.4901	0.2460	0.5124	0.4162	-	-	-	-	-	-	-	-	-	-
0.6061	5000	0.0193	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6303	5200	0.0223	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6545	5400	0.0117	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6788	5600	0.0254	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7030	5800	0.0197	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7273	6000	0.0271	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7515	6200	0.02	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7758	6400	0.0088	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8	6600	0.0125	0.0233	0.4945	0.2727	0.5212	0.4294	-	-	-	-	-	-	-	-	-	-
0.8242	6800	0.0214	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8485	7000	0.0147	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8727	7200	0.0192	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8970	7400	0.0135	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9212	7600	0.0086	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9455	7800	0.0205	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9697	8000	0.0267	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9939	8200	0.0149	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
1.0	8250	-	0.0174	0.4954	0.2631	0.5163	0.4250	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.4945	0.2727	0.5212	0.5109	0.2565	0.5342	0.7891	0.3255	0.7118	0.9096	0.3318	0.4417	0.5519	0.5016

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.083 kWh
Carbon Emitted: 0.032 kg of CO2
Hours Used: 0.285 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: 4.2.0.dev0
Transformers: 4.49.0
PyTorch: 2.6.0+cu124
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",
}

SpladeLoss

@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}

SparseMultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

FlopsLoss

@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
    }