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: 53.740159900184786
  energy_consumed: 0.13825542420719417
  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: 0.409
  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: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.62
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.38
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.62
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.72
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.603846580732656
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.529079365079365
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.535577429489216
            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: 0.4
            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: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.34
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.336
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.28600000000000003
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.02662938222230507
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.08583886950771044
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.10539572959638349
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.1390606096616216
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.33155673498755867
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4815555555555555
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.14591039936040862
            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: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            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: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.43
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.6
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.73
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.76
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6020077639360719
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5624999999999999
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5519887965031844
            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: 0.4066666666666667
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5933333333333334
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7066666666666667
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7733333333333334
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4066666666666667
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.25333333333333335
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.21333333333333335
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.15133333333333332
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.27887646074076833
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4352796231692368
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5184652431987945
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5796868698872072
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5124703598854289
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5243783068783068
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.411158875117603
            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: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.156
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.44
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.78
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6402220356297674
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.576079365079365
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5819739218018417
            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: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.35999999999999993
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.344
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.29200000000000004
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.018848269093365854
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07354907247001424
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09781289475269293
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.1418672876485781
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.33652365839683074
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4957698412698413
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.14165509490208594
            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: 0.56
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.56
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.23333333333333336
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.54
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.65
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.73
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.83
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6813657040884066
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.647301587301587
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6310147772294485
            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: 0.47333333333333333
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6333333333333334
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7133333333333333
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7999999999999999
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.47333333333333333
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.27111111111111114
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.22
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.15666666666666665
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.33294942303112196
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.46118302415667145
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5359376315842309
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6039557625495261
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5527037993716682
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5730502645502644
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4515479313111254
            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: 0.2
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.56
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.2
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.132
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.088
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.07833333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.24499999999999997
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.28333333333333327
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3473333333333333
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.27333419680435084
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3666031746031747
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.21266834216817831
            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: 0.74
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.86
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.92
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.94
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.74
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5866666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.556
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.484
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08366724054361292
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.16227352802558825
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.2213882427797012
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3353731792736538
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5972307350486245
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8152222222222223
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.45303559906331897
            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: 0.98
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.98
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.98
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.86
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.34666666666666657
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.20799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.8066666666666668
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.9433333333333332
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9433333333333332
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9433333333333332
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9054259418093692
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9133333333333333
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8844551282051283
            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: 0.5
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.62
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.22399999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2725793650793651
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4129047619047619
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4605714285714286
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5500873015873016
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.49585690755175454
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5641666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4425504355719097
            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: 0.84
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.92
            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: 0.84
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.316
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.17399999999999996
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.71
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.79
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.87
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.802663278529999
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8856666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.7334779802028212
            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: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.156
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.78
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6354592257726257
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5694126984126984
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5752130160409359
            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: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.35999999999999993
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.34
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.29
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.018848269093365854
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07354907247001424
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.0962744332142314
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.14178823626517886
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3352519406973144
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.49602380952380964
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.14142955254174144
            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: 0.56
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.56
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.23333333333333336
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.54
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.65
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.73
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.83
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6813657040884066
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.647301587301587
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6311451301239768
            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: 0.86
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.98
            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: 0.4
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7373333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.9353333333333333
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9733333333333334
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9966666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9283913808760963
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9166666666666665
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8996944444444444
            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: 0.54
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.76
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.82
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.54
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.37999999999999995
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.30400000000000005
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.204
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.11466666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.23766666666666666
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.31466666666666665
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4196666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.42030245497944485
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6498333333333332
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3374015286377059
            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: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.76
            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: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.25333333333333335
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17999999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09599999999999997
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.28
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.76
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.96
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.651941051318052
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5498571428571428
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5515326278659611
            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: 0.76
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.76
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2733333333333334
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17599999999999993
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.565
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.74
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.76
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.88
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7313116540920006
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6887698412698413
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6840924219150025
            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: 0.6326530612244898
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8571428571428571
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8775510204081632
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9795918367346939
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6326530612244898
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5986394557823129
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5265306122448979
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4326530612244897
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.0443108966783425
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.12651297913694023
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1807810185085916
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2908183366162545
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4946170299181126
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7585276967930031
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3733282842478698
            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: 0.5732810047095762
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7628571428571429
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8105808477237049
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8707378335949765
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5732810047095762
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.356305599162742
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.27281004709576134
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1866656200941915
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3370312131842067
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.512044128836203
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5718216761338938
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6465436195186451
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6117808847297039
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6785680645884727
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5323095762329995
            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-reconstruction")
# 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([[55.6462, 14.4637, 16.8866]])

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	0.38	0.4	0.44
dot_accuracy@3	0.62	0.52	0.64
dot_accuracy@5	0.72	0.62	0.78
dot_accuracy@10	0.84	0.68	0.8
dot_precision@1	0.38	0.4	0.44
dot_precision@3	0.2067	0.34	0.2133
dot_precision@5	0.144	0.336	0.16
dot_precision@10	0.084	0.286	0.084
dot_recall@1	0.38	0.0266	0.43
dot_recall@3	0.62	0.0858	0.6
dot_recall@5	0.72	0.1054	0.73
dot_recall@10	0.84	0.1391	0.76
dot_ndcg@10	0.6038	0.3316	0.602
dot_mrr@10	0.5291	0.4816	0.5625
dot_map@100	0.5356	0.1459	0.552
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	0.4067
dot_accuracy@3	0.5933
dot_accuracy@5	0.7067
dot_accuracy@10	0.7733
dot_precision@1	0.4067
dot_precision@3	0.2533
dot_precision@5	0.2133
dot_precision@10	0.1513
dot_recall@1	0.2789
dot_recall@3	0.4353
dot_recall@5	0.5185
dot_recall@10	0.5797
dot_ndcg@10	0.5125
dot_mrr@10	0.5244
dot_map@100	0.4112
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	0.44	0.42	0.56
dot_accuracy@3	0.66	0.54	0.7
dot_accuracy@5	0.78	0.58	0.78
dot_accuracy@10	0.84	0.7	0.86
dot_precision@1	0.44	0.42	0.56
dot_precision@3	0.22	0.36	0.2333
dot_precision@5	0.156	0.344	0.16
dot_precision@10	0.084	0.292	0.094
dot_recall@1	0.44	0.0188	0.54
dot_recall@3	0.66	0.0735	0.65
dot_recall@5	0.78	0.0978	0.73
dot_recall@10	0.84	0.1419	0.83
dot_ndcg@10	0.6402	0.3365	0.6814
dot_mrr@10	0.5761	0.4958	0.6473
dot_map@100	0.582	0.1417	0.631
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	0.4733
dot_accuracy@3	0.6333
dot_accuracy@5	0.7133
dot_accuracy@10	0.8
dot_precision@1	0.4733
dot_precision@3	0.2711
dot_precision@5	0.22
dot_precision@10	0.1567
dot_recall@1	0.3329
dot_recall@3	0.4612
dot_recall@5	0.5359
dot_recall@10	0.604
dot_ndcg@10	0.5527
dot_mrr@10	0.5731
dot_map@100	0.4515
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	0.2	0.74	0.86	0.5	0.84	0.42	0.42	0.56	0.86	0.54	0.28	0.6	0.6327
dot_accuracy@3	0.52	0.86	0.98	0.62	0.92	0.66	0.54	0.7	0.98	0.76	0.76	0.76	0.8571
dot_accuracy@5	0.56	0.92	0.98	0.64	0.96	0.78	0.58	0.78	0.98	0.82	0.9	0.76	0.8776
dot_accuracy@10	0.68	0.94	0.98	0.68	0.96	0.84	0.7	0.86	1.0	0.86	0.96	0.88	0.9796
dot_precision@1	0.2	0.74	0.86	0.5	0.84	0.42	0.42	0.56	0.86	0.54	0.28	0.6	0.6327
dot_precision@3	0.1933	0.5867	0.3467	0.3133	0.4733	0.22	0.36	0.2333	0.4	0.38	0.2533	0.2733	0.5986
dot_precision@5	0.132	0.556	0.208	0.224	0.316	0.156	0.34	0.16	0.268	0.304	0.18	0.176	0.5265
dot_precision@10	0.088	0.484	0.104	0.138	0.174	0.084	0.29	0.094	0.138	0.204	0.096	0.1	0.4327
dot_recall@1	0.0783	0.0837	0.8067	0.2726	0.42	0.42	0.0188	0.54	0.7373	0.1147	0.28	0.565	0.0443
dot_recall@3	0.245	0.1623	0.9433	0.4129	0.71	0.66	0.0735	0.65	0.9353	0.2377	0.76	0.74	0.1265
dot_recall@5	0.2833	0.2214	0.9433	0.4606	0.79	0.78	0.0963	0.73	0.9733	0.3147	0.9	0.76	0.1808
dot_recall@10	0.3473	0.3354	0.9433	0.5501	0.87	0.84	0.1418	0.83	0.9967	0.4197	0.96	0.88	0.2908
dot_ndcg@10	0.2733	0.5972	0.9054	0.4959	0.8027	0.6355	0.3353	0.6814	0.9284	0.4203	0.6519	0.7313	0.4946
dot_mrr@10	0.3666	0.8152	0.9133	0.5642	0.8857	0.5694	0.496	0.6473	0.9167	0.6498	0.5499	0.6888	0.7585
dot_map@100	0.2127	0.453	0.8845	0.4426	0.7335	0.5752	0.1414	0.6311	0.8997	0.3374	0.5515	0.6841	0.3733
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	0.5733
dot_accuracy@3	0.7629
dot_accuracy@5	0.8106
dot_accuracy@10	0.8707
dot_precision@1	0.5733
dot_precision@3	0.3563
dot_precision@5	0.2728
dot_precision@10	0.1867
dot_recall@1	0.337
dot_recall@3	0.512
dot_recall@5	0.5718
dot_recall@10	0.6465
dot_ndcg@10	0.6118
dot_mrr@10	0.6786
dot_map@100	0.5323
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	-	-	0.6253	0.3224	0.5893	0.5123	0.6112	0.3278	0.6352	0.5248	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0646	100	0.0542	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	200	0.0566	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	300	0.0455	0.0390	0.5697	0.3083	0.6074	0.4952	0.5709	0.3402	0.6637	0.5249	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	400	0.0445	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3232	500	0.0463	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	600	0.056	0.0454	0.5981	0.3334	0.6076	0.5130	0.6217	0.3417	0.6337	0.5324	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4525	700	0.0505	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	800	0.0549	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	900	0.0614	0.0350	0.6058	0.3401	0.6084	0.5181	0.6293	0.3178	0.6585	0.5352	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	1000	0.0519	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	1100	0.039	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	1200	0.045	0.0384	0.6045	0.3348	0.6124	0.5172	0.6227	0.3333	0.6829	0.5463	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8403	1300	0.0536	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	1400	0.0389	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9696	1500	0.0413	0.0401	0.6038	0.3316	0.602	0.5125	0.6402	0.3365	0.6814	0.5527	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	-	-	-	-	-	-	-	-	0.2733	0.5972	0.9054	0.4959	0.8027	0.6355	0.3353	0.6814	0.9284	0.4203	0.6519	0.7313	0.4946	0.6118

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.138 kWh
Carbon Emitted: 0.054 kg of CO2
Hours Used: 0.409 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}
}