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: 13.144676625187973
  energy_consumed: 0.03381684844736578
  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: 0.145
  hardware_used: 1 x NVIDIA GeForce RTX 3090
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: 0.4
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5
            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: 0.13333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1
            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: 0.4
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.43322728177988873
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.35121428571428576
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.36254438939466105
            name: Dot Map@100
          - type: query_active_dims
            value: 114.83999633789062
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9962374681758112
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 504.9510192871094
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9834561621359311
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.4
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5
            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: 0.13333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1
            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: 0.4
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.43322728177988873
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.35121428571428576
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.36254438939466105
            name: Dot Map@100
          - type: query_active_dims
            value: 114.83999633789062
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9962374681758112
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 504.9510192871094
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9834561621359311
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.42
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.44
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.48
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.20800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.172
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01025265789874976
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.024326098686792398
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.03315745551680213
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.058486915473213524
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.19719700869611326
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.35035714285714287
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.06408607089134896
            name: Dot Map@100
          - type: query_active_dims
            value: 185
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9939387982438896
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1286.7938232421875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9578404487503379
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.42
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.44
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.48
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.20800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.172
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01025265789874976
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.024326098686792398
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.03315745551680213
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.058486915473213524
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.19719700869611326
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.35035714285714287
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.06408607089134896
            name: Dot Map@100
          - type: query_active_dims
            value: 185
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9939387982438896
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1286.7938232421875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9578404487503379
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.36
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.56
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.12
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10000000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.05600000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.33
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.46
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.52
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3556861493087894
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.322
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.31376550096906575
            name: Dot Map@100
          - type: query_active_dims
            value: 98.22000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9967819932763022
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 841.8667602539062
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9724177065639898
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.36
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.56
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.12
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10000000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.05600000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.33
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.46
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.52
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3556861493087894
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.322
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.31376550096906575
            name: Dot Map@100
          - type: query_active_dims
            value: 98.22000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9967819932763022
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 841.8667602539062
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9724177065639898
            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: 0.24
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.39333333333333337
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.48
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.58
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.24
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16888888888888887
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.13600000000000004
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09933333333333333
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.14341755263291658
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.25144203289559747
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3310524851722674
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.42616230515773784
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3287034799282638
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3411904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.24679865375169194
            name: Dot Map@100
          - type: query_active_dims
            value: 132.6866658528646
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9956527532320011
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 812.3067522198979
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9733861885780781
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.3254945054945055
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.4843328100470958
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5676295133437991
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6615384615384615
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3254945054945055
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2203453689167975
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1832904238618524
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13404081632653062
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.17156366311931473
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.27243997398612047
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3368199222866662
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4238029847392705
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3726337418448364
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4264663726296379
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2989418038202097
            name: Dot Map@100
          - type: query_active_dims
            value: 234.31433094300914
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9923231003557103
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 808.1458433081926
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9735225134883626
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.28
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.36
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.46
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.11333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.084
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.05800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.09166666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.15333333333333332
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.17666666666666664
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.22466666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.19429559758090853
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.27672222222222226
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.15485373044420248
            name: Dot Map@100
          - type: query_active_dims
            value: 259.8599853515625
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9914861416240233
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1094.6026611328125
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9641372563681013
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.52
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.74
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.84
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.52
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4599999999999999
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.45199999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.384
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.04966217676438495
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.10354828293616407
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.16425525763608173
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2406829559845734
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.456594069464261
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6436666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3020935356938311
            name: Dot Map@100
          - type: query_active_dims
            value: 191.25999450683594
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9937337004617379
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 809.2098999023438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9734876515332435
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.58
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.58
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14800000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.56
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.63
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.7
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.8466666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.681545812563628
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6464126984126983
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6296549550854825
            name: Dot Map@100
          - type: query_active_dims
            value: 249.5399932861328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9918242581322937
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1358.960205078125
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9554760433432237
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.14
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.26
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.36
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.46
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.14
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.10666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.068
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.07933333333333334
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.157
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.2571666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.30074603174603176
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.21720208465433088
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.23057936507936508
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.17181110132538066
            name: Dot Map@100
          - type: query_active_dims
            value: 87.4000015258789
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971364916609043
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 517.6328735351562
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9830406633400447
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.48
            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: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.48
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.204
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.114
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.24
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.51
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.57
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.489382062974203
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5975555555555556
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.41273857719946977
            name: Dot Map@100
          - type: query_active_dims
            value: 151.22000122070312
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9950455408813085
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 904.4683837890625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9703666737504403
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.34
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.48
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.34
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.12
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07800000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.32666666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4466666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5406666666666666
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7106666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5024501622170336
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.45037301587301587
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.444050525697599
            name: Dot Map@100
          - type: query_active_dims
            value: 51.31999969482422
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9983185898796008
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 59.146453857421875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.998062169783847
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.28
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17199999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.05866666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.14766666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.17566666666666664
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2796666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.25565589285716384
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4341031746031745
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.16804725663907635
            name: Dot Map@100
          - type: query_active_dims
            value: 195.27999877929688
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9936019920457605
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1035.02685546875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9660891535460078
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.02
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.12
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.14
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.16
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.02
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.039999999999999994
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.028000000000000004
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.016
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.02
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.12
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.14
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.16
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.09097486504648661
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.06833333333333333
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.07512669033130494
            name: Dot Map@100
          - type: query_active_dims
            value: 1119.800048828125
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9633117079867596
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 936.6198120117188
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9693132883817667
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            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: 0.64
            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: 0.124
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.074
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.335
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.515
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.545
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.63
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4915918543191975
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4533333333333332
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4491987141282297
            name: Dot Map@100
          - type: query_active_dims
            value: 299.3399963378906
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9901926480460688
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 1136.7972412109375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9627548246769236
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.5714285714285714
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8163265306122449
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9591836734693877
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5714285714285714
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5578231292517006
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5387755102040817
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4265306122448979
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.03907945255462338
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1141786135299426
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.17607960990710933
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.26785623174003165
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4784358025208683
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7194120505344994
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3382724018630733
            name: Dot Map@100
          - type: query_active_dims
            value: 39.1020393371582
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9987188900027142
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 630.3636474609375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9793472365028197
            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, 'architecture': 'DistilBertForMaskedLM'})
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/splade-distilbert-base-uncased-gooaq-peft")
# Run inference
queries = [
    "how many days for doxycycline to work on sinus infection?",
]
documents = [
    '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.',
    'The average service life of a gas furnace is about 15 years, but the actual life span of an individual unit can vary greatly. There are a number of contributing factors that determine the age a furnace reaches: The quality of the equipment.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 30522] [3, 30522]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[93.4242, 28.8323, 33.3142]])

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	0.22	0.28	0.22	0.22	0.52	0.58	0.14	0.48	0.34	0.28	0.02	0.36	0.5714
dot_accuracy@3	0.4	0.42	0.36	0.28	0.74	0.66	0.26	0.64	0.48	0.58	0.12	0.54	0.8163
dot_accuracy@5	0.5	0.44	0.5	0.36	0.84	0.72	0.36	0.78	0.58	0.62	0.14	0.58	0.9592
dot_accuracy@10	0.7	0.48	0.56	0.46	0.88	0.88	0.46	0.84	0.74	0.8	0.16	0.64	1.0
dot_precision@1	0.22	0.28	0.22	0.22	0.52	0.58	0.14	0.48	0.34	0.28	0.02	0.36	0.5714
dot_precision@3	0.1333	0.2533	0.12	0.1133	0.46	0.22	0.1067	0.2667	0.16	0.24	0.04	0.1933	0.5578
dot_precision@5	0.1	0.208	0.1	0.084	0.452	0.148	0.104	0.204	0.12	0.172	0.028	0.124	0.5388
dot_precision@10	0.07	0.172	0.056	0.058	0.384	0.09	0.068	0.114	0.078	0.136	0.016	0.074	0.4265
dot_recall@1	0.22	0.0103	0.2	0.0917	0.0497	0.56	0.0793	0.24	0.3267	0.0587	0.02	0.335	0.0391
dot_recall@3	0.4	0.0243	0.33	0.1533	0.1035	0.63	0.157	0.4	0.4467	0.1477	0.12	0.515	0.1142
dot_recall@5	0.5	0.0332	0.46	0.1767	0.1643	0.7	0.2572	0.51	0.5407	0.1757	0.14	0.545	0.1761
dot_recall@10	0.7	0.0585	0.52	0.2247	0.2407	0.8467	0.3007	0.57	0.7107	0.2797	0.16	0.63	0.2679
dot_ndcg@10	0.4332	0.1972	0.3557	0.1943	0.4566	0.6815	0.2172	0.4894	0.5025	0.2557	0.091	0.4916	0.4784
dot_mrr@10	0.3512	0.3504	0.322	0.2767	0.6437	0.6464	0.2306	0.5976	0.4504	0.4341	0.0683	0.4533	0.7194
dot_map@100	0.3625	0.0641	0.3138	0.1549	0.3021	0.6297	0.1718	0.4127	0.4441	0.168	0.0751	0.4492	0.3383
query_active_dims	114.84	185.0	98.22	259.86	191.26	249.54	87.4	151.22	51.32	195.28	1119.8	299.34	39.102
query_sparsity_ratio	0.9962	0.9939	0.9968	0.9915	0.9937	0.9918	0.9971	0.995	0.9983	0.9936	0.9633	0.9902	0.9987
corpus_active_dims	504.951	1286.7938	841.8668	1094.6027	809.2099	1358.9602	517.6329	904.4684	59.1465	1035.0269	936.6198	1136.7972	630.3636
corpus_sparsity_ratio	0.9835	0.9578	0.9724	0.9641	0.9735	0.9555	0.983	0.9704	0.9981	0.9661	0.9693	0.9628	0.9793

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.24
dot_accuracy@3	0.3933
dot_accuracy@5	0.48
dot_accuracy@10	0.58
dot_precision@1	0.24
dot_precision@3	0.1689
dot_precision@5	0.136
dot_precision@10	0.0993
dot_recall@1	0.1434
dot_recall@3	0.2514
dot_recall@5	0.3311
dot_recall@10	0.4262
dot_ndcg@10	0.3287
dot_mrr@10	0.3412
dot_map@100	0.2468
query_active_dims	132.6867
query_sparsity_ratio	0.9957
corpus_active_dims	812.3068
corpus_sparsity_ratio	0.9734

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	0.3255
dot_accuracy@3	0.4843
dot_accuracy@5	0.5676
dot_accuracy@10	0.6615
dot_precision@1	0.3255
dot_precision@3	0.2203
dot_precision@5	0.1833
dot_precision@10	0.134
dot_recall@1	0.1716
dot_recall@3	0.2724
dot_recall@5	0.3368
dot_recall@10	0.4238
dot_ndcg@10	0.3726
dot_mrr@10	0.4265
dot_map@100	0.2989
query_active_dims	234.3143
query_sparsity_ratio	0.9923
corpus_active_dims	808.1458
corpus_sparsity_ratio	0.9735

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')",
    "document_regularizer_weight": 3e-05,
    "query_regularizer_weight": 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')",
    "document_regularizer_weight": 3e-05,
    "query_regularizer_weight": 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}
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_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	234.4946	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0646	200	90.2538	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0970	300	35.2404	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	400	15.0794	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1616	500	5.7405	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	600	2.6706	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1972	610	-	1.5711	0.1942	0.1431	0.1568	0.1647	-	-	-	-	-	-	-	-	-	-
0.2262	700	1.4867	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	800	0.9108	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2909	900	0.7938	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3232	1000	0.6679	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3555	1100	0.5505	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	1200	0.4851	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3943	1220	-	0.3510	0.3406	0.1831	0.2740	0.2659	-	-	-	-	-	-	-	-	-	-
0.4202	1300	0.4882	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4525	1400	0.4156	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4848	1500	0.452	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	1600	0.3446	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5495	1700	0.307	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	1800	0.3416	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5915	1830	-	0.2682	0.3942	0.1917	0.3140	0.3000	-	-	-	-	-	-	-	-	-	-
0.6141	1900	0.2875	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	2000	0.2989	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6787	2100	0.3032	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	2200	0.3843	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7434	2300	0.2845	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	2400	0.2838	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7886	2440	-	0.2365	0.4144	0.1952	0.3378	0.3158	-	-	-	-	-	-	-	-	-	-
0.8080	2500	0.2422	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8403	2600	0.2546	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8727	2700	0.2683	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	2800	0.2923	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9373	2900	0.301	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9696	3000	0.2796	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9858	3050	-	0.2284	0.4332	0.1972	0.3557	0.3287	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.4332	0.1972	0.3557	0.3726	0.1943	0.4566	0.6815	0.2172	0.4894	0.5025	0.2557	0.0910	0.4916	0.4784

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.034 kWh
Carbon Emitted: 0.013 kg of CO2
Hours Used: 0.145 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: 2.7.1+cu126
Accelerate: 1.5.1
Datasets: 2.21.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

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

SpladeLoss

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

SparseMultipleNegativesRankingLoss

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

FlopsLoss

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