metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - csr
  - generated_from_trainer
  - dataset_size:99000
  - loss:CSRLoss
  - loss:SparseMultipleNegativesRankingLoss
base_model: mixedbread-ai/mxbai-embed-large-v1
widget:
  - text: >-
      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]
  - text: >-
      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]
  - text: >-
      who was the first president of indian science congress meeting held in
      kolkata in 1914
  - text: >-
      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.
  - text: >-
      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: 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: 53.486914244267936
  energy_consumed: 0.1376039079919011
  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: 0.406
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: Sparse CSR model trained on Natural Questions
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 128
          type: NanoMSMARCO_128
        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: 0.8
            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: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.36
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.6
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5700574882386609
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.49757936507936507
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5099077397336835
            name: Dot Map@100
          - type: query_active_dims
            value: 128
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.96875
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 128
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.96875
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 128
          type: NanoNFCorpus_128
        metrics:
          - type: dot_accuracy@1
            value: 0.3
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2866666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.234
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.038852553787646696
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.060787676252818314
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.08871070532106025
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.1164679743390103
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.27742011622390783
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.41685714285714276
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1342268199818926
            name: Dot Map@100
          - type: query_active_dims
            value: 128
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.96875
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 128
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.96875
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 128
          type: NanoNQ_128
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.132
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.41
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.56
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.59
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.71
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5655257382100716
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5366666666666667
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5200476570220556
            name: Dot Map@100
          - type: query_active_dims
            value: 128
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.96875
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 128
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.96875
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 128
          type: NanoBEIR_mean_128
        metrics:
          - type: dot_accuracy@1
            value: 0.36666666666666664
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5733333333333334
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6266666666666666
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7200000000000001
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36666666666666664
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.23111111111111113
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17866666666666667
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13133333333333333
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.26961751792921557
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.40692922541760607
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.45290356844035345
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5421559914463367
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4710011142242134
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.48370105820105813
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3880607389125439
            name: Dot Map@100
          - type: query_active_dims
            value: 128
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.96875
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 128
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.96875
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO 256
          type: NanoMSMARCO_256
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.32
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.58
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.556581518059458
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.47826984126984123
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.49049453698389867
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus 256
          type: NanoNFCorpus_256
        metrics:
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.54
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.66
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.28800000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.258
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04394699993743869
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07346911892860693
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.0955352050901188
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.13423937941849148
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3138240971606582
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4724126984126984
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1554159267082162
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ 256
          type: NanoNQ_256
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.62
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.21333333333333335
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15200000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.59
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.79
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6092334692116076
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5592142857142858
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5537561375100075
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-nano-beir
          name: Sparse Nano BEIR
        dataset:
          name: NanoBEIR mean 256
          type: NanoBEIR_mean_256
        metrics:
          - type: dot_accuracy@1
            value: 0.38666666666666666
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5666666666666668
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7599999999999999
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38666666666666666
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19600000000000004
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14266666666666666
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2613156666458129
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.41448970630953563
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5051784016967064
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5747464598061639
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.49321302814390794
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5032989417989419
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.39988886706737414
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.34
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.34
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.21333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.176
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11799999999999997
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.14733333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.2723333333333333
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.359
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.469
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3709538178023985
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4734126984126983
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2810456840827194
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.78
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.88
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.78
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6666666666666665
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5880000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.484
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08494800977438213
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.17317448416542106
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.23034114850972465
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3258962243107224
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6091876327956771
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8355238095238097
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.45081375839318744
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.86
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.96
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.86
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19999999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.8066666666666668
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8666666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9266666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9266666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.8841127708415583
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.894
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8619688731284475
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.46
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.68
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.46
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.32666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.23199999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.25257936507936507
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4653809523809523
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5155952380952381
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.575563492063492
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5042980843824951
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5653333333333334
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4452452302579616
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.78
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.86
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.78
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.17199999999999996
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.39
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.75
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7821924588182537
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8334920634920635
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.7213993449971364
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.132
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.4
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.6
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.66
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.82
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5949657949660191
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5246825396825396
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5350828017012228
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            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: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.35999999999999993
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.292
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.262
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.03443480481548747
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.08039614346191623
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09609895574877417
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.1425768627754566
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3161920036806807
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4961031746031745
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1515139700880487
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.5
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.68
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.76
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.23333333333333336
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16399999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.088
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.47
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.64
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.78
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6331595818344276
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5986666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5865551394231594
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.92
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 1
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 1
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.92
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.40666666666666657
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.264
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7973333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.958
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.986
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9966666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9556238046457881
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9533333333333333
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.9349527472527472
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.58
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.82
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.58
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3999999999999999
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.292
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.206
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.12266666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.24966666666666665
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.30166666666666664
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.42166666666666663
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4272054291075693
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6870238095238096
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3390924092176022
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.78
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.82
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.94
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16399999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.36
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.78
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.82
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.94
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6626337389503802
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5724920634920635
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5758487068487068
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.6
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.78
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.27999999999999997
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.18
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.575
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.755
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.79
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.82
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.714313571551759
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6828888888888889
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6825983649369914
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.5918367346938775
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8571428571428571
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8979591836734694
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9591836734693877
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5918367346938775
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5374149659863945
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.4897959183673469
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4244897959183674
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.042649446100483254
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1077957848613647
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1613396254665287
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2701410353829605
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4710841185924516
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7299562682215744
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.34832336492939087
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            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: 0.5824489795918368
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7643956043956043
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8075353218210363
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8799372056514915
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5824489795918368
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3613396127681842
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.2687535321821036
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.18480690737833594
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.34489320198228596
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5152626178104862
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5682083308579691
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6421675088102025
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6096863698438044
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6805314345518426
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5318800304044093
            name: Dot Map@100
          - type: query_active_dims
            value: 256
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9375
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 256
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9375
            name: Corpus Sparsity Ratio

Sparse CSR model trained on Natural Questions

This is a CSR Sparse Encoder model finetuned from mixedbread-ai/mxbai-embed-large-v1 on the natural-questions dataset using the sentence-transformers library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space with 256 maximum active dimensions and can be used for semantic search and sparse retrieval.

Model Details

Model Description

Model Type: CSR Sparse Encoder
Base model: mixedbread-ai/mxbai-embed-large-v1
Maximum Sequence Length: 512 tokens
Output Dimensionality: 4096 dimensions (trained with 256 maximum active 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): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, '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 SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/csr-mxbai-embed-large-v1-nq-no-base-loss")
# Run inference
queries = [
    "who is cornelius in the book of acts",
]
documents = [
    '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]",
    '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.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[133.0582,  24.5010,  26.5905]])

Evaluation

Metrics

Sparse Information Retrieval

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

Metric	NanoMSMARCO_128	NanoNFCorpus_128	NanoNQ_128
dot_accuracy@1	0.36	0.3	0.44
dot_accuracy@3	0.6	0.52	0.6
dot_accuracy@5	0.68	0.58	0.62
dot_accuracy@10	0.8	0.62	0.74
dot_precision@1	0.36	0.3	0.44
dot_precision@3	0.2	0.2867	0.2067
dot_precision@5	0.136	0.268	0.132
dot_precision@10	0.08	0.234	0.08
dot_recall@1	0.36	0.0389	0.41
dot_recall@3	0.6	0.0608	0.56
dot_recall@5	0.68	0.0887	0.59
dot_recall@10	0.8	0.1165	0.71
dot_ndcg@10	0.5701	0.2774	0.5655
dot_mrr@10	0.4976	0.4169	0.5367
dot_map@100	0.5099	0.1342	0.52
query_active_dims	128.0	128.0	128.0
query_sparsity_ratio	0.9688	0.9688	0.9688
corpus_active_dims	128.0	128.0	128.0
corpus_sparsity_ratio	0.9688	0.9688	0.9688

Sparse Nano BEIR

Dataset: NanoBEIR_mean_128

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.3667
dot_accuracy@3	0.5733
dot_accuracy@5	0.6267
dot_accuracy@10	0.72
dot_precision@1	0.3667
dot_precision@3	0.2311
dot_precision@5	0.1787
dot_precision@10	0.1313
dot_recall@1	0.2696
dot_recall@3	0.4069
dot_recall@5	0.4529
dot_recall@10	0.5422
dot_ndcg@10	0.471
dot_mrr@10	0.4837
dot_map@100	0.3881
query_active_dims	128.0
query_sparsity_ratio	0.9688
corpus_active_dims	128.0
corpus_sparsity_ratio	0.9688

Sparse Information Retrieval

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

Metric	NanoMSMARCO_256	NanoNFCorpus_256	NanoNQ_256
dot_accuracy@1	0.32	0.4	0.44
dot_accuracy@3	0.58	0.5	0.62
dot_accuracy@5	0.74	0.54	0.7
dot_accuracy@10	0.8	0.66	0.82
dot_precision@1	0.32	0.4	0.44
dot_precision@3	0.1933	0.3133	0.2133
dot_precision@5	0.148	0.288	0.152
dot_precision@10	0.08	0.258	0.09
dot_recall@1	0.32	0.0439	0.42
dot_recall@3	0.58	0.0735	0.59
dot_recall@5	0.74	0.0955	0.68
dot_recall@10	0.8	0.1342	0.79
dot_ndcg@10	0.5566	0.3138	0.6092
dot_mrr@10	0.4783	0.4724	0.5592
dot_map@100	0.4905	0.1554	0.5538
query_active_dims	256.0	256.0	256.0
query_sparsity_ratio	0.9375	0.9375	0.9375
corpus_active_dims	256.0	256.0	256.0
corpus_sparsity_ratio	0.9375	0.9375	0.9375

Sparse Nano BEIR

Dataset: NanoBEIR_mean_256

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.3867
dot_accuracy@3	0.5667
dot_accuracy@5	0.66
dot_accuracy@10	0.76
dot_precision@1	0.3867
dot_precision@3	0.24
dot_precision@5	0.196
dot_precision@10	0.1427
dot_recall@1	0.2613
dot_recall@3	0.4145
dot_recall@5	0.5052
dot_recall@10	0.5747
dot_ndcg@10	0.4932
dot_mrr@10	0.5033
dot_map@100	0.3999
query_active_dims	256.0
query_sparsity_ratio	0.9375
corpus_active_dims	256.0
corpus_sparsity_ratio	0.9375

Sparse Information Retrieval

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

Metric	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
dot_accuracy@1	0.34	0.78	0.86	0.46	0.78	0.4	0.4	0.5	0.92	0.58	0.36	0.6	0.5918
dot_accuracy@3	0.54	0.88	0.9	0.68	0.86	0.6	0.58	0.68	1.0	0.8	0.78	0.78	0.8571
dot_accuracy@5	0.7	0.9	0.96	0.68	0.9	0.66	0.6	0.76	1.0	0.82	0.82	0.8	0.898
dot_accuracy@10	0.82	0.96	0.96	0.74	1.0	0.82	0.74	0.8	1.0	0.88	0.94	0.82	0.9592
dot_precision@1	0.34	0.78	0.86	0.46	0.78	0.4	0.4	0.5	0.92	0.58	0.36	0.6	0.5918
dot_precision@3	0.2133	0.6667	0.3133	0.3267	0.5	0.2	0.36	0.2333	0.4067	0.4	0.26	0.28	0.5374
dot_precision@5	0.176	0.588	0.2	0.232	0.32	0.132	0.292	0.164	0.264	0.292	0.164	0.18	0.4898
dot_precision@10	0.118	0.484	0.1	0.14	0.172	0.082	0.262	0.088	0.138	0.206	0.094	0.094	0.4245
dot_recall@1	0.1473	0.0849	0.8067	0.2526	0.39	0.4	0.0344	0.47	0.7973	0.1227	0.36	0.575	0.0426
dot_recall@3	0.2723	0.1732	0.8667	0.4654	0.75	0.6	0.0804	0.64	0.958	0.2497	0.78	0.755	0.1078
dot_recall@5	0.359	0.2303	0.9267	0.5156	0.8	0.66	0.0961	0.74	0.986	0.3017	0.82	0.79	0.1613
dot_recall@10	0.469	0.3259	0.9267	0.5756	0.86	0.82	0.1426	0.78	0.9967	0.4217	0.94	0.82	0.2701
dot_ndcg@10	0.371	0.6092	0.8841	0.5043	0.7822	0.595	0.3162	0.6332	0.9556	0.4272	0.6626	0.7143	0.4711
dot_mrr@10	0.4734	0.8355	0.894	0.5653	0.8335	0.5247	0.4961	0.5987	0.9533	0.687	0.5725	0.6829	0.73
dot_map@100	0.281	0.4508	0.862	0.4452	0.7214	0.5351	0.1515	0.5866	0.935	0.3391	0.5758	0.6826	0.3483
query_active_dims	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0
query_sparsity_ratio	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375
corpus_active_dims	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0	256.0
corpus_sparsity_ratio	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375	0.9375

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	0.5824
dot_accuracy@3	0.7644
dot_accuracy@5	0.8075
dot_accuracy@10	0.8799
dot_precision@1	0.5824
dot_precision@3	0.3613
dot_precision@5	0.2688
dot_precision@10	0.1848
dot_recall@1	0.3449
dot_recall@3	0.5153
dot_recall@5	0.5682
dot_recall@10	0.6422
dot_ndcg@10	0.6097
dot_mrr@10	0.6805
dot_map@100	0.5319
query_active_dims	256.0
query_sparsity_ratio	0.9375
corpus_active_dims	256.0
corpus_sparsity_ratio	0.9375

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": 1.0,
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}

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": 1.0,
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
learning_rate: 4e-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: 64
per_device_eval_batch_size: 64
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: 0.0
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
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
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_128_dot_ndcg@10	NanoNFCorpus_128_dot_ndcg@10	NanoNQ_128_dot_ndcg@10	NanoBEIR_mean_128_dot_ndcg@10	NanoMSMARCO_256_dot_ndcg@10	NanoNFCorpus_256_dot_ndcg@10	NanoNQ_256_dot_ndcg@10	NanoBEIR_mean_256_dot_ndcg@10	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10
-1	-1	-	-	0.5667	0.2784	0.6350	0.4933	0.6324	0.2927	0.6451	0.5234	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0646	100	0.2571	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	200	0.2333	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	300	0.2251	0.2188	0.6315	0.2816	0.5812	0.4981	0.5986	0.3188	0.6332	0.5169	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	400	0.2203	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3232	500	0.2172	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	600	0.2148	0.2090	0.6205	0.2824	0.5906	0.4978	0.5804	0.3145	0.6514	0.5155	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4525	700	0.2131	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	800	0.2114	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	900	0.2103	0.2044	0.6134	0.2956	0.5787	0.4959	0.5765	0.3134	0.6116	0.5005	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	1000	0.2093	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	1100	0.2086	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	1200	0.2081	0.2020	0.5954	0.2884	0.5542	0.4794	0.5806	0.3105	0.6062	0.4991	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8403	1300	0.2075	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	1400	0.2074	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9696	1500	0.207	0.2011	0.5701	0.2774	0.5655	0.4710	0.5566	0.3138	0.6092	0.4932	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	-	-	-	0.3710	0.6092	0.8841	0.5043	0.7822	0.5950	0.3162	0.6332	0.9556	0.4272	0.6626	0.7143	0.4711	0.6097

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.138 kWh
Carbon Emitted: 0.053 kg of CO2
Hours Used: 0.406 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: 4.52.4
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",
}

CSRLoss

@misc{wen2025matryoshkarevisitingsparsecoding,
      title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
      author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
      year={2025},
      eprint={2503.01776},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2503.01776},
}

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}
}