Add new SparseEncoder model

ba9d67b verified 3 months ago

76.6 kB

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: 16.638146863146233
  energy_consumed: 0.04280437678001716
  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: 0.193
  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: 0.3
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3
            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: 0.07400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.54
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.74
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5061981336542133
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.43174603174603166
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.44263003895418085
            name: Dot Map@100
          - type: query_active_dims
            value: 118.5999984741211
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.996114278275535
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 397.6775817871094
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9869707888805744
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16666666666666663
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.128
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07200000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.32
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.5
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.64
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.72
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5061402921245981
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.43823809523809515
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4500866595693115
            name: Dot Map@100
          - type: query_active_dims
            value: 105.08000183105469
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.996557237342538
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 381.3874816894531
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9875045055471643
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.34
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.44
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.48
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.34
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.23199999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.19599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.01204138289831077
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.028423242145972874
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.04013720529494631
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.06944452178864681
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2238211925399539
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4057777777777777
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.07440414426513103
            name: Dot Map@100
          - type: query_active_dims
            value: 183.05999755859375
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9940023590341854
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 823.3663940429688
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9730238387378621
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.3
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.48
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.23199999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.21400000000000002
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.010708049564977435
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.04042324214597287
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.05817733939406678
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.0849823575856454
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.24157503472859507
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3932222222222223
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.08415340735361837
            name: Dot Map@100
          - type: query_active_dims
            value: 150.77999877929688
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9950599567925006
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 807.0741577148438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9735576253943109
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.28
            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: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            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: 0.07
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.27
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.48
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.54
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.64
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.45385561138570657
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.40454761904761893
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.40238133013339067
            name: Dot Map@100
          - type: query_active_dims
            value: 108.23999786376953
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9964537055938743
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 581.3165893554688
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9809541776634733
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.24
            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: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.24
            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: 0.07400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.23
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.44
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.51
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.67
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4431148339670733
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3818015873015873
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3762054598208147
            name: Dot Map@100
          - type: query_active_dims
            value: 97.18000030517578
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.996816067089143
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 564.0422973632812
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9815201396578442
            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: 0.3066666666666667
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.49333333333333335
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.5800000000000001
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.6733333333333333
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.3066666666666667
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20222222222222222
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16133333333333333
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.11333333333333334
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1940137942994369
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.34947441404865764
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4200457350983155
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4831481739295489
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.39462497919329126
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4140238095238094
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3064718377842342
            name: Dot Map@100
          - type: query_active_dims
            value: 136.63333129882812
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9955234476345315
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 565.0999949325504
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9814854860450642
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.35158555729984303
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5366091051805337
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.609105180533752
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7153218210361068
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.35158555729984303
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24084772370486657
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.195861852433281
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14448037676609105
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.18710365017134828
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.3166600122342838
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.38032257819651705
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4791896835492342
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.41388777461576925
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4636842715108021
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.33650048535941457
            name: Dot Map@100
          - type: query_active_dims
            value: 195.48228298827937
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9935953645570972
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 525.5023385946348
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9827828340674059
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.2
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.38
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.42
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.52
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.2
            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: 0.06000000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08833333333333332
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.18166666666666664
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.19233333333333336
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2523333333333333
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2097369113981719
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.2989603174603175
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.16798141398273245
            name: Dot Map@100
          - type: query_active_dims
            value: 250.86000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9917810103987172
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 643.326904296875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9789225180428257
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.62
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.78
            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: 0.62
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4733333333333334
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.452
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.39599999999999996
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.06769969786296744
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.14199136819511296
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.192778624550143
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2816492423802407
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4998791588316728
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7168571428571429
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3705445544087827
            name: Dot Map@100
          - type: query_active_dims
            value: 146.02000427246094
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9952159096955487
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 481.7581481933594
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9842160360332429
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.156
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.44
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.64
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.7366666666666666
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7966666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6190748153469672
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5678888888888888
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5644736817593311
            name: Dot Map@100
          - type: query_active_dims
            value: 253.3800048828125
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9916984468618435
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 749.9185180664062
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9754302300613852
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.22
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.42
            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: 0.22
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16666666666666663
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.13933333333333334
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.26035714285714284
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.31182539682539684
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3924047619047619
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3071601294876744
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3309126984126985
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2510011498241125
            name: Dot Map@100
          - type: query_active_dims
            value: 85.69999694824219
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9971921893405333
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 416.93829345703125
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9863397453162627
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.68
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.78
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.88
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.68
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.35333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.24
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.34
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.53
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.6
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.69
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6197567693807055
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7347142857142859
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.540453368331375
            name: Dot Map@100
          - type: query_active_dims
            value: 152.5399932861328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9950022936476596
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 553.4066772460938
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9818685971677447
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.124
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.34666666666666673
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4706666666666666
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5506666666666666
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7506666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5326024015174656
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4782936507936508
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4734890338060357
            name: Dot Map@100
          - type: query_active_dims
            value: 52.900001525878906
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982668238802871
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 61.35552978515625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9979897932709142
            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: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.28
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.184
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13799999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.059666666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.12866666666666668
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.18966666666666662
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.2836666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.2574919427490159
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.42540476190476184
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.17688082476501285
            name: Dot Map@100
          - type: query_active_dims
            value: 197.1999969482422
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9935390866604993
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 676.0037231445312
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9778519191683201
            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: 0.14
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.22
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.38
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.02
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.04666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.044000000000000004
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.038000000000000006
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.02
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.14
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.22
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.38
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.17464966621739791
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.11243650793650796
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.11564322909400383
            name: Dot Map@100
          - type: query_active_dims
            value: 732.4600219726562
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9760022271812904
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 648.47509765625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9787538464826602
            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: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.66
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.132
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.078
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.335
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.535
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.575
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.66
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5064687965907525
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4627222222222222
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.46039157929311386
            name: Dot Map@100
          - type: query_active_dims
            value: 276.20001220703125
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9909507891944489
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 729.4652099609375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9761003469641264
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.5306122448979592
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7959183673469388
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9183673469387755
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9591836734693877
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5306122448979592
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5510204081632653
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5102040816326532
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4122448979591837
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.03493970479958239
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.10780840584746129
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.16707882245178216
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.26709619093606257
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.4628903176649091
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6864431486880467
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.34320194766414486
            name: Dot Map@100
          - type: query_active_dims
            value: 37.81632614135742
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9987610141490939
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 493.48040771484375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9838319766819067
            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-r128")
# 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([[85.3246, 22.8328, 29.6908]])

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	0.32	0.3	0.24	0.2	0.62	0.44	0.22	0.68	0.36	0.28	0.02	0.36	0.5306
dot_accuracy@3	0.5	0.46	0.46	0.38	0.78	0.66	0.42	0.78	0.52	0.52	0.14	0.56	0.7959
dot_accuracy@5	0.64	0.48	0.54	0.42	0.86	0.78	0.46	0.8	0.58	0.62	0.22	0.6	0.9184
dot_accuracy@10	0.72	0.6	0.72	0.52	0.92	0.84	0.54	0.88	0.78	0.78	0.38	0.66	0.9592
dot_precision@1	0.32	0.3	0.24	0.2	0.62	0.44	0.22	0.68	0.36	0.28	0.02	0.36	0.5306
dot_precision@3	0.1667	0.2733	0.1533	0.14	0.4733	0.22	0.1667	0.3533	0.1733	0.2067	0.0467	0.2067	0.551
dot_precision@5	0.128	0.232	0.108	0.092	0.452	0.156	0.144	0.24	0.124	0.184	0.044	0.132	0.5102
dot_precision@10	0.072	0.214	0.074	0.06	0.396	0.086	0.09	0.138	0.082	0.138	0.038	0.078	0.4122
dot_recall@1	0.32	0.0107	0.23	0.0883	0.0677	0.44	0.1393	0.34	0.3467	0.0597	0.02	0.335	0.0349
dot_recall@3	0.5	0.0404	0.44	0.1817	0.142	0.64	0.2604	0.53	0.4707	0.1287	0.14	0.535	0.1078
dot_recall@5	0.64	0.0582	0.51	0.1923	0.1928	0.7367	0.3118	0.6	0.5507	0.1897	0.22	0.575	0.1671
dot_recall@10	0.72	0.085	0.67	0.2523	0.2816	0.7967	0.3924	0.69	0.7507	0.2837	0.38	0.66	0.2671
dot_ndcg@10	0.5061	0.2416	0.4431	0.2097	0.4999	0.6191	0.3072	0.6198	0.5326	0.2575	0.1746	0.5065	0.4629
dot_mrr@10	0.4382	0.3932	0.3818	0.299	0.7169	0.5679	0.3309	0.7347	0.4783	0.4254	0.1124	0.4627	0.6864
dot_map@100	0.4501	0.0842	0.3762	0.168	0.3705	0.5645	0.251	0.5405	0.4735	0.1769	0.1156	0.4604	0.3432
query_active_dims	105.08	150.78	97.18	250.86	146.02	253.38	85.7	152.54	52.9	197.2	732.46	276.2	37.8163
query_sparsity_ratio	0.9966	0.9951	0.9968	0.9918	0.9952	0.9917	0.9972	0.995	0.9983	0.9935	0.976	0.991	0.9988
corpus_active_dims	381.3875	807.0742	564.0423	643.3269	481.7581	749.9185	416.9383	553.4067	61.3555	676.0037	648.4751	729.4652	493.4804
corpus_sparsity_ratio	0.9875	0.9736	0.9815	0.9789	0.9842	0.9754	0.9863	0.9819	0.998	0.9779	0.9788	0.9761	0.9838

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.3067
dot_accuracy@3	0.4933
dot_accuracy@5	0.58
dot_accuracy@10	0.6733
dot_precision@1	0.3067
dot_precision@3	0.2022
dot_precision@5	0.1613
dot_precision@10	0.1133
dot_recall@1	0.194
dot_recall@3	0.3495
dot_recall@5	0.42
dot_recall@10	0.4831
dot_ndcg@10	0.3946
dot_mrr@10	0.414
dot_map@100	0.3065
query_active_dims	136.6333
query_sparsity_ratio	0.9955
corpus_active_dims	565.1
corpus_sparsity_ratio	0.9815

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	0.3516
dot_accuracy@3	0.5366
dot_accuracy@5	0.6091
dot_accuracy@10	0.7153
dot_precision@1	0.3516
dot_precision@3	0.2408
dot_precision@5	0.1959
dot_precision@10	0.1445
dot_recall@1	0.1871
dot_recall@3	0.3167
dot_recall@5	0.3803
dot_recall@10	0.4792
dot_ndcg@10	0.4139
dot_mrr@10	0.4637
dot_map@100	0.3365
query_active_dims	195.4823
query_sparsity_ratio	0.9936
corpus_active_dims	525.5023
corpus_sparsity_ratio	0.9828

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	81.7292	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0646	200	4.3059	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0970	300	0.8078	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1293	400	0.4309	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1616	500	0.3837	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1939	600	0.282	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1972	610	-	0.1867	0.4508	0.2059	0.3905	0.3491	-	-	-	-	-	-	-	-	-	-
0.2262	700	0.2593	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2586	800	0.2161	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2909	900	0.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3232	1000	0.2259	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3555	1100	0.2161	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3878	1200	0.1835	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3943	1220	-	0.1368	0.4567	0.2373	0.4209	0.3717	-	-	-	-	-	-	-	-	-	-
0.4202	1300	0.1936	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4525	1400	0.1689	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4848	1500	0.1858	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5171	1600	0.1639	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5495	1700	0.1376	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5818	1800	0.1677	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5915	1830	-	0.1138	0.5061	0.2416	0.4431	0.3969	-	-	-	-	-	-	-	-	-	-
0.6141	1900	0.1483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6464	2000	0.1513	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6787	2100	0.1449	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	2200	0.193	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7434	2300	0.1554	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7757	2400	0.1372	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7886	2440	-	0.1148	0.5084	0.2240	0.4428	0.3917	-	-	-	-	-	-	-	-	-	-
0.8080	2500	0.1308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8403	2600	0.1284	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8727	2700	0.1309	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9050	2800	0.1458	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9373	2900	0.1351	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9696	3000	0.1135	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9858	3050	-	0.1068	0.5062	0.2238	0.4539	0.3946	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.5061	0.2416	0.4431	0.4139	0.2097	0.4999	0.6191	0.3072	0.6198	0.5326	0.2575	0.1746	0.5065	0.4629

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.043 kWh
Carbon Emitted: 0.017 kg of CO2
Hours Used: 0.193 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}
}