metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:90000
  - loss:SpladeLoss
  - loss:SparseMarginMSELoss
  - loss:FlopsLoss
base_model: Luyu/co-condenser-marco
widget:
  - text: where was pandora vanderpump born
  - text: how old is jay sekulow
  - text: >-
      Quick Answer. According to Domino Sugar, 1 pound of granulated sugar
      contains approximately 2 1/4 cups of sugar. Therefore, in a 4-pound
      package, the cook gets an average of 9 cups of sugar for baking. Continue
      Reading.
  - text: why did rachel hunter and rod stewart divorce
  - text: "Lake Poinsett. Home > Florida Lakes > Lake Poinsett. Lake Poinsett BASS ONLINE 2016-10-18T14:26:01+00:00. Lake Poinsett Fishing. As the St. Johns River snakes out of Lake Washington and through the lush, green marshes, it eventually forms a â\x80\x98minorâ\x80\x99 wide spot in its trace some eight miles to the North."
datasets:
  - sentence-transformers/msmarco
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
model-index:
  - name: >-
      splade-co-condenser-marco trained on MS MARCO hard negatives with
      distillation
    results:
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoMSMARCO
          type: NanoMSMARCO
        metrics:
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            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: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.38
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.82
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6023892381130012
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5322460317460317
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5403716431832851
            name: Dot Map@100
          - type: query_active_dims
            value: 47.2599983215332
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984516087307014
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 140.00595092773438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9954129496452482
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.68
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.76
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.22666666666666668
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.15200000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.38
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.68
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.76
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.82
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6107820870126021
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5426666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5509587519225252
            name: Dot Map@100
          - type: query_active_dims
            value: 47.400001525878906
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984470217703336
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 140.1564483642578
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9954080188596993
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.32666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32400000000000007
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.264
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.023844509223146355
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07793005806894508
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09810315520586681
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.12354566164984142
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3101256773824815
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.46361111111111114
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.13411049507814402
            name: Dot Map@100
          - type: query_active_dims
            value: 46.79999923706055
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984666797969641
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 213.68675231933594
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9929989269274839
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.36
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.36
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.31999999999999995
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.264
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.024013480037278462
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07918359732248433
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09829476070182012
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.12458300696889957
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.31048812326644165
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4638571428571429
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.13575571099602127
            name: Dot Map@100
          - type: query_active_dims
            value: 46.63999938964844
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984719219124025
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 215.3623504638672
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9929440288819912
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.5
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.72
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24666666666666665
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.088
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.46
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.67
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.73
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.79
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6404985476355836
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6148888888888888
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5893974971543039
            name: Dot Map@100
          - type: query_active_dims
            value: 54.7599983215332
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982058843351834
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 159.0401153564453
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9947893285054568
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.5
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.74
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.088
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.46
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.69
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.73
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.79
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6425696161474067
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6180555555555555
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5913323140802889
            name: Dot Map@100
          - type: query_active_dims
            value: 55.279998779296875
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.998188847428763
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 160.6440887451172
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9947367771199425
            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: 0.41333333333333333
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6266666666666667
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7133333333333333
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7866666666666666
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.41333333333333333
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2644444444444444
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.2106666666666667
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14466666666666664
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.2879481697410488
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.46931001935631506
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5227010517352889
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5778485538832805
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.517671154377022
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5369153439153439
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.42129321180524437
            name: Dot Map@100
          - type: query_active_dims
            value: 49.60666529337565
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9983747242876162
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 164.05755283149915
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.994624940933376
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.5333751962323391
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7058712715855572
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7721821036106752
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8522762951334379
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5333751962323391
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.33272632129774987
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26023861852433283
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.18210989010989007
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3065495560101058
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.47065760019746655
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5319234205921822
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6150942444263999
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5745069781714651
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6371311579576886
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.49203911035247966
            name: Dot Map@100
          - type: query_active_dims
            value: 74.83821266421184
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.997548056724192
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 164.48360193811445
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9946109821788182
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            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: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.1733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.098
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.15899999999999997
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.23566666666666664
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.2956666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3846666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3249781769970352
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4319047619047619
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.2561474960874848
            name: Dot Map@100
          - type: query_active_dims
            value: 110.87999725341797
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.996367210626649
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 192.7664337158203
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9936843446132029
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.78
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.86
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.78
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6799999999999998
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.6080000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.516
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.0805494021375943
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.16994266800080168
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.23707620669389493
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.33886339859207476
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6340309872443929
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8339682539682539
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4790982179197883
            name: Dot Map@100
          - type: query_active_dims
            value: 48.70000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984044295667734
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 181.08651733398438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9940670166655532
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.76
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.92
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.76
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.30666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19199999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7166666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8533333333333333
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8833333333333333
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9433333333333332
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.8471518983952602
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.836857142857143
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8095613973839781
            name: Dot Map@100
          - type: query_active_dims
            value: 76.31999969482422
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9974995085612075
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 218.5546417236328
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9928394390366412
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.5
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.74
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.21333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16799999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.22607936507936507
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.29846825396825394
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4133253968253968
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5269920634920634
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.41629394858564644
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.48766666666666664
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.35228818600065076
            name: Dot Map@100
          - type: query_active_dims
            value: 52.36000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982845160667599
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 134.6856231689453
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9955872608882462
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.84
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.94
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.96
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.98
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.84
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.4733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.31999999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.17199999999999996
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.42
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.71
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.8
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.7969477208305935
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.895
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.7206139921516787
            name: Dot Map@100
          - type: query_active_dims
            value: 81.45999908447266
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.997331105462143
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 189.1210174560547
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9938037803074485
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.82
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 1
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 1
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.82
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.38666666666666655
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.25199999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7440000000000001
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.938
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9686666666666668
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.99
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9198144942648507
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9033333333333333
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8868987080103358
            name: Dot Map@100
          - type: query_active_dims
            value: 50.97999954223633
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9983297293905302
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 54.81371307373047
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9982041244651816
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.42
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.58
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.66
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.82
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.228
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.16399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08766666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.16966666666666666
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.2346666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3356666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.32595965166383967
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5274920634920635
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.24854805230092453
            name: Dot Map@100
          - type: query_active_dims
            value: 77.0999984741211
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9974739532640678
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 191.10289001464844
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9937388477159214
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.14
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            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: 0.14
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.15333333333333332
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.11600000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07400000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.14
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.46
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.58
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.74
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.431363004003593
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.33355555555555555
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.345556865044935
            name: Dot Map@100
          - type: query_active_dims
            value: 184.3800048828125
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.993959111300609
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 172.4982147216797
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9943483973946111
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.52
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.72
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.52
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16399999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.71
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.725
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.83
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6741722815754707
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.625079365079365
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6257231669822414
            name: Dot Map@100
          - type: query_active_dims
            value: 93.36000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.996941222704595
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 216.22164916992188
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9929158754613091
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.6938775510204082
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8163265306122449
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9183673469387755
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9795918367346939
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6938775510204082
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6054421768707483
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5551020408163266
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4714285714285715
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.047168647543802934
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1242876166088582
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.18897477014392502
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3121200418234938
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5340387262419134
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7832685455134434
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3940255757013834
            name: Dot Map@100
          - type: query_active_dims
            value: 47.48979568481445
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9984440798216102
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 139.98329162597656
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9954136920376785
            name: Corpus Sparsity Ratio

splade-co-condenser-marco trained on MS MARCO hard negatives with distillation

This is a SPLADE Sparse Encoder model finetuned from Luyu/co-condenser-marco on the msmarco 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: Luyu/co-condenser-marco
Maximum Sequence Length: 256 tokens
Output Dimensionality: 30522 dimensions
Similarity Function: Dot Product
Training Dataset:
- msmarco
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': 'BertForMaskedLM'})
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("arthurbresnu/splade-co-condenser-marco-msmarco-qwen3-reranker-0.6B-margin-mse")
# Run inference
queries = [
    "what town is grand lake st mary near",
]
documents = [
    'Grand Lake St. Marys State Park. Grand Lake St. Marys State Park is an American state park, west of St. Marys, and south-east of Celina, 23 miles (37 km) south-west of Lima in the north-western part of Ohio. Grand Lake covers 13,500 acres (5,500 ha) in Mercer and Auglaize counties.',
    'Lake Poinsett. Home > Florida Lakes > Lake Poinsett. Lake Poinsett BASS ONLINE 2016-10-18T14:26:01+00:00. Lake Poinsett Fishing. As the St. Johns River snakes out of Lake Washington and through the lush, green marshes, it eventually forms a â\x80\x98minorâ\x80\x99 wide spot in its trace some eight miles to the North.',
    'Slavery in America began when the first African slaves were brought to the North American colony of Jamestown, Virginia, in 1619, to aid in the production of such lucrative crops as tobacco.',
]
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([[23.0166, 12.0320,  1.7877]])

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	0.38	0.36	0.5	0.32	0.78	0.76	0.4	0.84	0.82	0.42	0.14	0.52	0.6939
dot_accuracy@3	0.68	0.5	0.74	0.48	0.86	0.9	0.5	0.94	1.0	0.58	0.46	0.72	0.8163
dot_accuracy@5	0.76	0.62	0.78	0.58	0.9	0.92	0.62	0.96	1.0	0.66	0.58	0.74	0.9184
dot_accuracy@10	0.82	0.7	0.82	0.72	0.96	0.96	0.74	0.98	1.0	0.82	0.74	0.84	0.9796
dot_precision@1	0.38	0.36	0.5	0.32	0.78	0.76	0.4	0.84	0.82	0.42	0.14	0.52	0.6939
dot_precision@3	0.2267	0.32	0.2533	0.1733	0.68	0.3067	0.2133	0.4733	0.3867	0.2733	0.1533	0.26	0.6054
dot_precision@5	0.152	0.328	0.16	0.14	0.608	0.192	0.168	0.32	0.252	0.228	0.116	0.164	0.5551
dot_precision@10	0.082	0.264	0.088	0.098	0.516	0.104	0.106	0.172	0.134	0.164	0.074	0.094	0.4714
dot_recall@1	0.38	0.024	0.46	0.159	0.0805	0.7167	0.2261	0.42	0.744	0.0877	0.14	0.5	0.0472
dot_recall@3	0.68	0.0792	0.69	0.2357	0.1699	0.8533	0.2985	0.71	0.938	0.1697	0.46	0.71	0.1243
dot_recall@5	0.76	0.0983	0.73	0.2957	0.2371	0.8833	0.4133	0.8	0.9687	0.2347	0.58	0.725	0.189
dot_recall@10	0.82	0.1246	0.79	0.3847	0.3389	0.9433	0.527	0.86	0.99	0.3357	0.74	0.83	0.3121
dot_ndcg@10	0.6108	0.3105	0.6426	0.325	0.634	0.8472	0.4163	0.7969	0.9198	0.326	0.4314	0.6742	0.534
dot_mrr@10	0.5427	0.4639	0.6181	0.4319	0.834	0.8369	0.4877	0.895	0.9033	0.5275	0.3336	0.6251	0.7833
dot_map@100	0.551	0.1358	0.5913	0.2561	0.4791	0.8096	0.3523	0.7206	0.8869	0.2485	0.3456	0.6257	0.394
query_active_dims	47.4	46.64	55.28	110.88	48.7	76.32	52.36	81.46	50.98	77.1	184.38	93.36	47.4898
query_sparsity_ratio	0.9984	0.9985	0.9982	0.9964	0.9984	0.9975	0.9983	0.9973	0.9983	0.9975	0.994	0.9969	0.9984
corpus_active_dims	140.1564	215.3624	160.6441	192.7664	181.0865	218.5546	134.6856	189.121	54.8137	191.1029	172.4982	216.2216	139.9833
corpus_sparsity_ratio	0.9954	0.9929	0.9947	0.9937	0.9941	0.9928	0.9956	0.9938	0.9982	0.9937	0.9943	0.9929	0.9954

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.4133
dot_accuracy@3	0.6267
dot_accuracy@5	0.7133
dot_accuracy@10	0.7867
dot_precision@1	0.4133
dot_precision@3	0.2644
dot_precision@5	0.2107
dot_precision@10	0.1447
dot_recall@1	0.2879
dot_recall@3	0.4693
dot_recall@5	0.5227
dot_recall@10	0.5778
dot_ndcg@10	0.5177
dot_mrr@10	0.5369
dot_map@100	0.4213
query_active_dims	49.6067
query_sparsity_ratio	0.9984
corpus_active_dims	164.0576
corpus_sparsity_ratio	0.9946

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	0.5334
dot_accuracy@3	0.7059
dot_accuracy@5	0.7722
dot_accuracy@10	0.8523
dot_precision@1	0.5334
dot_precision@3	0.3327
dot_precision@5	0.2602
dot_precision@10	0.1821
dot_recall@1	0.3065
dot_recall@3	0.4707
dot_recall@5	0.5319
dot_recall@10	0.6151
dot_ndcg@10	0.5745
dot_mrr@10	0.6371
dot_map@100	0.492
query_active_dims	74.8382
query_sparsity_ratio	0.9975
corpus_active_dims	164.4836
corpus_sparsity_ratio	0.9946

Training Details

Training Dataset

msmarco

Dataset: msmarco at 9e329ed
Size: 90,000 training samples
Columns: query, positive, negative, and score

Approximate statistics based on the first 1000 samples:

	query	positive	negative	score
type	string	string	string	float
details	min: 4 tokens mean: 9.05 tokens max: 22 tokens	min: 17 tokens mean: 79.74 tokens max: 228 tokens	min: 14 tokens mean: 77.68 tokens max: 256 tokens	min: -3.38 mean: 10.51 max: 21.0

Samples:

query	positive	negative	score
`journal entries for standard cost variances`	1 Fiber Optic, Inc., investigates all variances above 10 percent of the flexible budget. 2 The flexible budget for direct materials is $50,000. 3 The direct materials price variance is $4,000 unfavorable and the direct materials quantity variance is $(6,000) favorable. Assuming a standard price of $5 per yard, prepare a journal entry to record the purchase of raw materials for the month. 2 The company used 39,000 yards of material in production for the month, and the flexible budget shows the company expected to use 40,800 yards.	`In accounting the monthly close is the processing of transactions, journal entries and financial statements at the end of each month.`	`9.375`
`what county in pana, il in?`	`Pana /ËpeÉªnÉ/ is a city in Christian County, Illinois, United States. The population was 5,614 at the 2000 census.`	`Burr Ridge, IL is currently using an area code overlay in which area codes 331 and 630 serve the same geographic area. Ten digit dialing (area code + seven digit number) is necessary. In addition to Burr Ridge, IL area code information read more about area codes 331 and 630 details and Illinois area codes. Burr Ridge, IL is located in DuPage County and observes the Central Time Zone. View our Times by Area Code tool.`	`13.75`
`when was keep on loving you released`	`Share this page. REO's first Top 40 appearance proved to be a fruitful one, with the group taking Keep on Loving You to the number one spot in December of 1980.`	Description: âIf Loving You Is Wrongâ is the new dramatic series created for television by writer/director Tyler Perry, premiering this fall on OWN. âIf Loving You Is Wrongâ is the compelling story of several women from very different walks of life.ack to the Have and The Have Nots, the scenes are too long and the characters are one dimensional. If it wasn't for Tika Sumpter, the show would be unbearable to watch. Love Thy Neighbor is the worst show ever. It is a throwback to blackface mistrel shows.	`8.875`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMarginMSELoss",
    "document_regularizer_weight": 0.08,
    "query_regularizer_weight": 0.1
}

Evaluation Dataset

msmarco

Dataset: msmarco at 9e329ed
Size: 10,000 evaluation samples
Columns: query, positive, negative, and score

Approximate statistics based on the first 1000 samples:

	query	positive	negative	score
type	string	string	string	float
details	min: 4 tokens mean: 9.22 tokens max: 43 tokens	min: 19 tokens mean: 80.19 tokens max: 209 tokens	min: 14 tokens mean: 77.78 tokens max: 239 tokens	min: -9.0 mean: 10.74 max: 21.75

Samples:

query	positive	negative	score
`what trump said about obama playing golf during campaign`	`Obama also has played golf with Woods during his presidency, though typically the presidentâs golf partners are personal friends and select aides, as opposed to celebrities. At a campaign rally in December 2015, Trump ripped into Obama for playing hundreds of rounds of golf as president. âHe played more golf last year than Tiger Woods,â Trump said suggestively. âWe donât have time for this. We have to work.â.`	`Trump slams Obama, Clinton for 'politically correct' war against ISIS, warns of more attacks. Republican presidential nominee Donald Trump has accused the Obama administration of waging a 'politically correct' war against the ISIS terror group and warned that more terror attacks would take place.`	`8.421875`
`how much volume is a gram`	`One gram is equal to 0.0353 ounces. A gram of sugar is approximately 1/4 teaspoon of sugar. A regular paper clip weighs about 1 gram. The gram and kilogram are units of mass in the metric system of measurement. The metric system was invented in France in 1799. It was improved in 1960 and named the System of International Units, or SI.`	Divide the object's mass by its volume. This value is the object's density and expresses it in units of mass per unit of volume. For example, for a 20-gram mass that takes up a volume of 5 cubic centimeters, the density is 4 grams per cubic centimeter.Ad.ivide the object's mass by its volume. This value is the object's density and expresses it in units of mass per unit of volume. For example, for a 20-gram mass that takes up a volume of 5 cubic centimeters, the density is 4 grams per cubic centimeter. Ad.	`2.65625`
`differences between the sexes`	`sexual dimorphism in birds can be manifested in size or plumage differences between the sexes sexual size dimorphism varies among taxa with males typically being larger though this is not always the case i e birds of prey hummingbirds and some species of flightless birds`	`Caribou are the only species of deer in which both sexes have antlers. Mature bulls can carry enormous and complex antlers, whereas cows and young animals generally have smaller and simpler ones. Mature bulls usually shed their antlers shortly after the rut whereas cows can keep theirs until spring.`	`10.21875`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMarginMSELoss",
    "document_regularizer_weight": 0.08,
    "query_regularizer_weight": 0.1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
bf16: True
load_best_model_at_end: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 0.1
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
hub_revision: None
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
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
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
0.0178	100	576200.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0356	200	2635.0334	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0533	300	70.7781	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0711	400	46.7365	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0889	500	33.3391	46.8835	0.5158	0.2778	0.6192	0.4709	-	-	-	-	-	-	-	-	-	-
0.1067	600	29.4815	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1244	700	27.123	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1422	800	22.7267	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.16	900	22.2125	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1778	1000	23.7129	22.1341	0.5768	0.2807	0.5689	0.4754	-	-	-	-	-	-	-	-	-	-
0.1956	1100	23.1061	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2133	1200	23.3015	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2311	1300	19.0495	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2489	1400	20.465	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2667	1500	19.5227	18.4953	0.5447	0.2930	0.5663	0.4680	-	-	-	-	-	-	-	-	-	-
0.2844	1600	19.7019	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3022	1700	20.2723	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.32	1800	18.644	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3378	1900	17.8863	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3556	2000	17.824	21.6579	0.5722	0.2951	0.5739	0.4804	-	-	-	-	-	-	-	-	-	-
0.3733	2100	18.2091	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3911	2200	17.9996	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4089	2300	15.7506	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4267	2400	17.8921	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4444	2500	16.3761	20.0396	0.5493	0.2811	0.6257	0.4854	-	-	-	-	-	-	-	-	-	-
0.4622	2600	18.1791	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.48	2700	15.3429	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4978	2800	14.9936	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5156	2900	15.364	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5333	3000	15.6449	17.3149	0.5672	0.3030	0.6095	0.4932	-	-	-	-	-	-	-	-	-	-
0.5511	3100	15.6673	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5689	3200	15.0578	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5867	3300	15.906	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6044	3400	15.6495	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6222	3500	13.6636	14.5839	0.5683	0.2978	0.6191	0.4951	-	-	-	-	-	-	-	-	-	-
0.64	3600	14.7215	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6578	3700	15.1004	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6756	3800	13.7198	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6933	3900	13.9975	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	4000	13.5657	14.8618	0.5983	0.3042	0.6183	0.5069	-	-	-	-	-	-	-	-	-	-
0.7289	4100	13.8326	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7467	4200	14.5209	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7644	4300	13.4064	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7822	4400	13.7625	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8	4500	13.2154	14.3594	0.5734	0.3266	0.6345	0.5115	-	-	-	-	-	-	-	-	-	-
0.8178	4600	13.7091	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8356	4700	12.5913	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8533	4800	12.433	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8711	4900	13.0404	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8889	5000	12.409	14.0825	0.6108	0.3105	0.6426	0.5213	-	-	-	-	-	-	-	-	-	-
0.9067	5100	12.4556	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9244	5200	12.4219	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9422	5300	12.4269	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.96	5400	12.5363	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9778	5500	12.4979	13.8156	0.6024	0.3101	0.6405	0.5177	-	-	-	-	-	-	-	-	-	-
0.9956	5600	11.9616	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.6108	0.3105	0.6426	0.5745	0.3250	0.6340	0.8472	0.4163	0.7969	0.9198	0.3260	0.4314	0.6742	0.5340

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.13.3
Sentence Transformers: 4.2.0.dev0
Transformers: 4.53.0
PyTorch: 2.7.1+cu126
Accelerate: 1.8.1
Datasets: 3.6.0
Tokenizers: 0.21.2

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},
}

SparseMarginMSELoss

@misc{hofstätter2021improving,
    title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation},
    author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
    year={2021},
    eprint={2010.02666},
    archivePrefix={arXiv},
    primaryClass={cs.IR}
}

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}
}