metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:99000
  - loss:SpladeLoss
  - loss:SparseMultipleNegativesRankingLoss
  - loss:FlopsLoss
base_model: distilbert/distilbert-base-uncased
widget:
  - text: >-
      The term emergent literacy signals a belief that, in a literate society,
      young children even one and two year olds, are in the process of becoming
      literate”. ... Gray (1956:21) notes: Functional literacy is used for the
      training of adults to 'meet independently the reading and writing demands
      placed on them'.
  - text: >-
      Rey is seemingly confirmed as being The Chosen One per a quote by a
      Lucasfilm production designer who worked on The Rise of Skywalker.
  - text: are union gun safes fireproof?
  - text: >-
      Fruit is an essential part of a healthy diet — and may aid weight loss.
      Most fruits are low in calories while high in nutrients and fiber, which
      can boost your fullness. Keep in mind that it's best to eat fruits whole
      rather than juiced. What's more, simply eating fruit is not the key to
      weight loss.
  - text: >-
      Treatment of suspected bacterial infection is with antibiotics, such as
      amoxicillin/clavulanate or doxycycline, given for 5 to 7 days for acute
      sinusitis and for up to 6 weeks for chronic sinusitis.
datasets:
  - sentence-transformers/gooaq
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: 1.0881870582723092
  energy_consumed: 0.019418388234485075
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD Ryzen 9 6900HX with Radeon Graphics
  ram_total_size: 30.6114501953125
  hours_used: 0.174
  hardware_used: 1 x NVIDIA GeForce RTX 3070 Ti Laptop GPU
model-index:
  - name: splade-distilbert-base-uncased trained on GooAQ
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.54
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.15333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10800000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.22
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.46
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.54
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.44470504856183124
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3652460317460317
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.37928248813494486
            name: Dot Map@100
          - type: query_active_dims
            value: 125.86000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9958764169906837
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 296.2349853515625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9902943783057611
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.24
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.24
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16666666666666663
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.11600000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07200000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.24
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.58
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.72
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.47847271089832977
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.40169047619047615
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4140044816294816
            name: Dot Map@100
          - type: query_active_dims
            value: 109.69999694824219
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9964058712748758
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 265.6180725097656
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9912974879591847
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.56
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.58
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2866666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.276
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.20400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.020432228546915038
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.05966030415500706
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.08546529551494754
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.10325648585391117
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2586742055175529
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.444
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.10277044614671307
            name: Dot Map@100
          - type: query_active_dims
            value: 160.10000610351562
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9947546030370383
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 409.76904296875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.986574633281936
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.52
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.66
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.29333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.268
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.22799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.03979891140267026
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.05843303142773433
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.07656018207627424
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.10998150964383814
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.28162049888840096
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4571904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.11433559983443616
            name: Dot Map@100
          - type: query_active_dims
            value: 140.05999755859375
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9954111789018218
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 371.9038391113281
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9878152205258068
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.18
            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: 0.3
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.62
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5013957867971872
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4491904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.44262111936629595
            name: Dot Map@100
          - type: query_active_dims
            value: 128.39999389648438
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9957931985487031
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 359.4007873535156
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9882248611705158
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.19333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.078
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.34
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.54
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.63
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.69
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5189963924532662
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4757777777777777
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.46913515575703424
            name: Dot Map@100
          - type: query_active_dims
            value: 115.30000305175781
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9962223968595846
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 336.913818359375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9889616074189316
            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: 0.3
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5800000000000001
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6733333333333332
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17333333333333334
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.180144076182305
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.339886768051669
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4151550985049825
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.501085495284637
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.40159168029219044
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.41947883597883595
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.30822468454931795
            name: Dot Map@100
          - type: query_active_dims
            value: 138.12000020345053
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9954747395254749
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 346.36973212643693
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9886518009263339
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.4301726844583988
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6182417582417583
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6783359497645213
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7722135007849293
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4301726844583988
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.274160125588697
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.21524646781789644
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.1563861852433281
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.24332694326060123
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.38912806185875454
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4466126446755131
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5378480354517308
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.48091561944614786
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5383367720714658
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.40550699373209664
            name: Dot Map@100
          - type: query_active_dims
            value: 161.59013707612073
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9947057814993735
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 302.84806046588795
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.99007771245443
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.26
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.4
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.42
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.64
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.26
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.14
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.09200000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.13
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.18
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.19
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.30733333333333335
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2528315611912319
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3483253968253968
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.195000428587257
            name: Dot Map@100
          - type: query_active_dims
            value: 215.39999389648438
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9929427955606944
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 334.818359375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9890302614712339
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.54
            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: 0.9
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.54
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.43333333333333335
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.4
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.35999999999999993
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04725330037285543
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.09136010229983793
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.12256470056683391
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.24664786941021674
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.43054704834652313
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6440714285714284
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3239717199251123
            name: Dot Map@100
          - type: query_active_dims
            value: 147.72000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9951602122658835
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 295.1452331542969
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9903300821324194
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.56
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.78
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.86
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.92
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.56
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.172
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.096
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5466666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.7466666666666666
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8066666666666668
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8766666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7202530021492869
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6843809523809523
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6647642136958143
            name: Dot Map@100
          - type: query_active_dims
            value: 201.5399932861328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9933968942636088
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 374.9945983886719
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9877139571984578
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.54
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.168
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.106
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.18857936507936507
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.3216825396825396
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3532380952380953
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4552380952380953
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3784249151812378
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.44319047619047613
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.31981273776184116
            name: Dot Map@100
          - type: query_active_dims
            value: 87.62000274658203
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971292837053083
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 275.46795654296875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9909747737191872
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.66
            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: 0.92
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.66
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.2879999999999999
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.15599999999999997
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.33
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.65
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.72
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.78
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6985941766475363
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7596666666666667
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.632578269203448
            name: Dot Map@100
          - type: query_active_dims
            value: 131.75999450683594
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9956831139995139
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 330.9889831542969
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9891557242921729
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.58
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.76
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.86
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.94
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.58
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.184
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.57
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.7233333333333334
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8233333333333333
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8953333333333333
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7379320795882585
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6864126984126984
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6882004324782192
            name: Dot Map@100
          - type: query_active_dims
            value: 56.70000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9981423235448876
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 63.429447174072266
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9979218449913483
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            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: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.228
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.154
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08466666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.15866666666666668
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.23566666666666666
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.31666666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.307302076202993
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5031111111111111
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2314013330851555
            name: Dot Map@100
          - type: query_active_dims
            value: 219.97999572753906
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9927927398031735
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 370.2647399902344
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.98786892274457
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.1
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.38
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.46
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.54
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.1
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.12666666666666665
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.09200000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.05400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.38
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.46
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.54
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.314067080699688
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.24191269841269844
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2544871127158089
            name: Dot Map@100
          - type: query_active_dims
            value: 392.3999938964844
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.98714369982647
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 371.9895324707031
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9878124129326157
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.54
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.54
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.505
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.6
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.635
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.76
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6330847757650383
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6099365079365079
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5921039809068559
            name: Dot Map@100
          - type: query_active_dims
            value: 239.02000427246094
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9921689271911257
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 362.61492919921875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9881195554288966
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.6122448979591837
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8571428571428571
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9183673469387755
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9387755102040817
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6122448979591837
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5374149659863945
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5102040816326532
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4510204081632653
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04128535219959204
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.10852246408702973
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.17293473623380118
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.29415698658034994
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4997767347881314
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7427113702623908
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.37179545293679184
            name: Dot Map@100
          - type: query_active_dims
            value: 41.06122589111328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9986547006784905
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 307.7058410644531
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9899185557609445
            name: Corpus Sparsity Ratio

splade-distilbert-base-uncased trained on GooAQ

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

Model Details

Model Description

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

Model Sources

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

Full Model Architecture

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

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("arthurbresnu/splade-distilbert-base-uncased-gooaq")
# Run inference
sentences = [
    'how many days for doxycycline to work on sinus infection?',
    'Treatment of suspected bacterial infection is with antibiotics, such as amoxicillin/clavulanate or doxycycline, given for 5 to 7 days for acute sinusitis and for up to 6 weeks for chronic sinusitis.',
    'Most engagements typically have a cocktail dress code, calling for dresses at, or slightly above, knee-length and high heels. If your party states a different dress code, however, such as semi-formal or dressy-casual, you may need to dress up or down accordingly.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 30522)

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

Evaluation

Metrics

Sparse Information Retrieval

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

Metric	NanoMSMARCO	NanoNFCorpus	NanoNQ	NanoClimateFEVER	NanoDBPedia	NanoFEVER	NanoFiQA2018	NanoHotpotQA	NanoQuoraRetrieval	NanoSCIDOCS	NanoArguAna	NanoSciFact	NanoTouche2020
dot_accuracy@1	0.24	0.38	0.36	0.26	0.54	0.56	0.36	0.66	0.58	0.4	0.1	0.54	0.6122
dot_accuracy@3	0.5	0.5	0.58	0.4	0.68	0.78	0.52	0.86	0.76	0.58	0.38	0.64	0.8571
dot_accuracy@5	0.58	0.52	0.66	0.42	0.76	0.86	0.54	0.92	0.86	0.66	0.46	0.66	0.9184
dot_accuracy@10	0.72	0.66	0.72	0.64	0.9	0.92	0.62	0.92	0.94	0.74	0.54	0.78	0.9388
dot_precision@1	0.24	0.38	0.36	0.26	0.54	0.56	0.36	0.66	0.58	0.4	0.1	0.54	0.6122
dot_precision@3	0.1667	0.2933	0.1933	0.14	0.4333	0.26	0.2467	0.4333	0.26	0.2533	0.1267	0.22	0.5374
dot_precision@5	0.116	0.268	0.136	0.092	0.4	0.172	0.168	0.288	0.184	0.228	0.092	0.144	0.5102
dot_precision@10	0.072	0.228	0.078	0.08	0.36	0.096	0.106	0.156	0.112	0.154	0.054	0.086	0.451
dot_recall@1	0.24	0.0398	0.34	0.13	0.0473	0.5467	0.1886	0.33	0.57	0.0847	0.1	0.505	0.0413
dot_recall@3	0.5	0.0584	0.54	0.18	0.0914	0.7467	0.3217	0.65	0.7233	0.1587	0.38	0.6	0.1085
dot_recall@5	0.58	0.0766	0.63	0.19	0.1226	0.8067	0.3532	0.72	0.8233	0.2357	0.46	0.635	0.1729
dot_recall@10	0.72	0.11	0.69	0.3073	0.2466	0.8767	0.4552	0.78	0.8953	0.3167	0.54	0.76	0.2942
dot_ndcg@10	0.4785	0.2816	0.519	0.2528	0.4305	0.7203	0.3784	0.6986	0.7379	0.3073	0.3141	0.6331	0.4998
dot_mrr@10	0.4017	0.4572	0.4758	0.3483	0.6441	0.6844	0.4432	0.7597	0.6864	0.5031	0.2419	0.6099	0.7427
dot_map@100	0.414	0.1143	0.4691	0.195	0.324	0.6648	0.3198	0.6326	0.6882	0.2314	0.2545	0.5921	0.3718
query_active_dims	109.7	140.06	115.3	215.4	147.72	201.54	87.62	131.76	56.7	219.98	392.4	239.02	41.0612
query_sparsity_ratio	0.9964	0.9954	0.9962	0.9929	0.9952	0.9934	0.9971	0.9957	0.9981	0.9928	0.9871	0.9922	0.9987
corpus_active_dims	265.6181	371.9038	336.9138	334.8184	295.1452	374.9946	275.468	330.989	63.4294	370.2647	371.9895	362.6149	307.7058
corpus_sparsity_ratio	0.9913	0.9878	0.989	0.989	0.9903	0.9877	0.991	0.9892	0.9979	0.9879	0.9878	0.9881	0.9899

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.3
dot_accuracy@3	0.5
dot_accuracy@5	0.58
dot_accuracy@10	0.6733
dot_precision@1	0.3
dot_precision@3	0.2067
dot_precision@5	0.1733
dot_precision@10	0.118
dot_recall@1	0.1801
dot_recall@3	0.3399
dot_recall@5	0.4152
dot_recall@10	0.5011
dot_ndcg@10	0.4016
dot_mrr@10	0.4195
dot_map@100	0.3082
query_active_dims	138.12
query_sparsity_ratio	0.9955
corpus_active_dims	346.3697
corpus_sparsity_ratio	0.9887

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	0.4302
dot_accuracy@3	0.6182
dot_accuracy@5	0.6783
dot_accuracy@10	0.7722
dot_precision@1	0.4302
dot_precision@3	0.2742
dot_precision@5	0.2152
dot_precision@10	0.1564
dot_recall@1	0.2433
dot_recall@3	0.3891
dot_recall@5	0.4466
dot_recall@10	0.5378
dot_ndcg@10	0.4809
dot_mrr@10	0.5383
dot_map@100	0.4055
query_active_dims	161.5901
query_sparsity_ratio	0.9947
corpus_active_dims	302.8481
corpus_sparsity_ratio	0.9901

Training Details

Training Dataset

gooaq

Dataset: gooaq at b089f72
Size: 99,000 training samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.79 tokens
max: 24 tokens

min: 14 tokens
mean: 60.02 tokens
max: 153 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.79 tokens max: 24 tokens	min: 14 tokens mean: 60.02 tokens max: 153 tokens

Samples:

question	answer
`what are the 5 characteristics of a star?`	`Key Concept: Characteristics used to classify stars include color, temperature, size, composition, and brightness.`
`are copic markers alcohol ink?`	`Copic Ink is alcohol-based and flammable. Keep away from direct sunlight and extreme temperatures.`
`what is the difference between appellate term and appellate division?`	`Appellate terms An appellate term is an intermediate appellate court that hears appeals from the inferior courts within their designated counties or judicial districts, and are intended to ease the workload on the Appellate Division and provide a less expensive forum closer to the people.`

Loss: SpladeLoss with these parameters:

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

Evaluation Dataset

gooaq

Dataset: gooaq at b089f72
Size: 1,000 evaluation samples
Columns: question and answer
Approximate statistics based on the first 1000 samples:
question answer
type string string
details
min: 8 tokens
mean: 11.93 tokens
max: 25 tokens

min: 14 tokens
mean: 60.84 tokens
max: 127 tokens

	question	answer
type	string	string
details	min: 8 tokens mean: 11.93 tokens max: 25 tokens	min: 14 tokens mean: 60.84 tokens max: 127 tokens

Samples:

question	answer
`should you take ibuprofen with high blood pressure?`	`In general, people with high blood pressure should use acetaminophen or possibly aspirin for over-the-counter pain relief. Unless your health care provider has said it's OK, you should not use ibuprofen, ketoprofen, or naproxen sodium. If aspirin or acetaminophen doesn't help with your pain, call your doctor.`
`how old do you have to be to work in sc?`	`The general minimum age of employment for South Carolina youth is 14, although the state allows younger children who are performers to work in show business. If their families are agricultural workers, children younger than age 14 may also participate in farm labor.`
`how to write a topic proposal for a research paper?`	`['Write down the main topic of your paper. ... ', 'Write two or three short sentences under the main topic that explain why you chose that topic. ... ', 'Write a thesis sentence that states the angle and purpose of your research paper. ... ', 'List the items you will cover in the body of the paper that support your thesis statement.']`

Loss: SpladeLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 2e-05
num_train_epochs: 1
bf16: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
tp_size: 0
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10
0.0323	100	15.2006	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0646	200	0.2384	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0970	300	0.1932	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	400	0.1428	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1616	500	0.144	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	600	0.1345	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1972	610	-	0.1199	0.4364	0.2195	0.4998	0.3853	-	-	-	-	-	-	-	-	-	-
0.2262	700	0.1406	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	800	0.1012	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2909	900	0.112	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3232	1000	0.0736	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3555	1100	0.0943	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	1200	0.0901	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3943	1220	-	0.1126	0.4706	0.2490	0.5154	0.4117	-	-	-	-	-	-	-	-	-	-
0.4202	1300	0.0988	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4525	1400	0.0953	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4848	1500	0.1145	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	1600	0.0928	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5495	1700	0.0963	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	1800	0.0724	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5915	1830	-	0.0736	0.4576	0.2457	0.5015	0.4016	-	-	-	-	-	-	-	-	-	-
0.6141	1900	0.0753	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	2000	0.0657	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6787	2100	0.0741	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	2200	0.0671	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7434	2300	0.1013	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	2400	0.0795	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7886	2440	-	0.0719	0.4785	0.2816	0.519	0.4264	-	-	-	-	-	-	-	-	-	-
0.8080	2500	0.0666	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8403	2600	0.0589	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8727	2700	0.0569	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	2800	0.0754	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9373	2900	0.0724	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9696	3000	0.0658	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9858	3050	-	0.0661	0.4447	0.2587	0.5014	0.4016	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.4785	0.2816	0.5190	0.4809	0.2528	0.4305	0.7203	0.3784	0.6986	0.7379	0.3073	0.3141	0.6331	0.4998

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.019 kWh
Carbon Emitted: 0.001 kg of CO2
Hours Used: 0.174 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3070 Ti Laptop GPU
CPU Model: AMD Ryzen 9 6900HX with Radeon Graphics
RAM Size: 30.61 GB

Framework Versions

Python: 3.12.9
Sentence Transformers: 4.2.0.dev0
Transformers: 4.50.3
PyTorch: 2.6.0+cu124
Accelerate: 1.6.0
Datasets: 3.5.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

SpladeLoss

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

SparseMultipleNegativesRankingLoss

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

FlopsLoss

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