Hugging Face's logo

sparse-encoder
/
example-splade-co-condenser-marco-msmarco-mse-margin

Feature Extraction
sentence-transformers
Safetensors
English
bert
sparse-encoder
sparse
splade
Generated from Trainer
dataset_size:90000
loss:SpladeLoss
loss:SparseMarginMSELoss
loss:FlopsLoss
Eval Results
text-embeddings-inference
Model card Files Community
example-splade-co-condenser-marco-msmarco-mse-margin / README.md
arthurbresnu's picture
arthurbresnu HF Staff
Add new SparseEncoder model
c6cad00 verified
preview code
|
raw
history blame contribute delete
91.8 kB
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: how old do you have to be to have lasik
  - text: when is house of cards on netflix
  - text: >-
      Answer by lauryn (194). The length of time it takes a women to get her
      period after giving birth varies from women to women. For many women it
      can take about 2 to 3 months before your period returns to normal. If you
      are nursing than this time frame will last even longer.
  - text: what are cys residues
  - text: "You heard about fastest cars, bikes and plans but today we have world fastest bird collection. In our collection we have top 10 fastest birds of the world. Birdâ\x80\x99s flight speed is fundamentally changeable; a hunting bird speed will increase while diving-to-catch prey as compared to its gliding speeds. Here we have the top 10 fastest birds with their flight speed. 10. Teal 109 km/h (68mph) This bird can fly 109 km/ h (68mph); they are 53 to 59cm long. This bird always lives in group. 09."
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
co2_eq_emissions:
  emissions: 34.21475343773813
  energy_consumed: 0.0926891546467269
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD EPYC 7R13 Processor
  ram_total_size: 248
  hours_used: 0.305
  hardware_used: 1 x NVIDIA H100 80GB HBM3
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: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.62
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.4
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.62
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6076647728795561
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5352777777777777
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5419469179877314
            name: Dot Map@100
          - type: query_active_dims
            value: 54.119998931884766
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982268527969371
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 187.67538452148438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.993851143944647
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.4
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.62
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.68
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.20666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.136
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08399999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.4
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.62
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.84
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6076647728795561
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5352777777777777
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5419469179877314
            name: Dot Map@100
          - type: query_active_dims
            value: 54.119998931884766
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982268527969371
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 187.67538452148438
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.993851143944647
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.34
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.316
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.27
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.06311467051346893
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.09895898433766803
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1169352131561954
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.14677603057730104
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.34523070842752446
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5258333333333334
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.16994217536385264
            name: Dot Map@100
          - type: query_active_dims
            value: 51.70000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9983061398085663
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 336.32476806640625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9889809066225539
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.64
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.34
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.316
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.27
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.06311467051346893
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.09895898433766803
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.1169352131561954
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.14677603057730104
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.34523070842752446
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5258333333333334
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.16994217536385264
            name: Dot Map@100
          - type: query_active_dims
            value: 51.70000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9983061398085663
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 336.32476806640625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9889809066225539
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNQ
          type: NanoNQ
        metrics:
          - type: dot_accuracy@1
            value: 0.52
            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: 0.84
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.52
            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: 0.08999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.48
            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: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6594960548473345
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6369365079365078
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6105143613696246
            name: Dot Map@100
          - type: query_active_dims
            value: 53.34000015258789
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982524080940768
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 223.5908660888672
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9926744359449294
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.52
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.74
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.78
            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: 0.2533333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.48
            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: 0.8
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6594960548473345
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6369365079365078
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6105143613696246
            name: Dot Map@100
          - type: query_active_dims
            value: 53.34000015258789
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982524080940768
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 223.5908660888672
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9926744359449294
            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: 0.45333333333333337
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6533333333333333
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7000000000000001
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7866666666666666
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.45333333333333337
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26666666666666666
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.204
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.148
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.314371556837823
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4696529947792227
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5089784043853984
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5955920101924337
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5374638453848051
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.566015873015873
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4408011515737362
            name: Dot Map@100
          - type: query_active_dims
            value: 53.0533332824707
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982618002331933
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 235.2385860639544
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9922928187515905
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.5580533751962323
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7137205651491366
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7722448979591837
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8291679748822605
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.5580533751962323
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3332705389848246
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26179591836734695
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.179171114599686
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.32499349487208484
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4721752731683537
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5337131771857326
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6042058945750339
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.578707182604652
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6493701377987092
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5041070229886567
            name: Dot Map@100
          - type: query_active_dims
            value: 86.67950763908115
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.997160097384212
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 230.5675761418069
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.992445856230201
            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: 0.52
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.54
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.165
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.26
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.28733333333333333
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.32233333333333336
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.30365156381250225
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4207222222222222
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.25580876542561
            name: Dot Map@100
          - type: query_active_dims
            value: 135.3000030517578
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.99556713180487
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 270.1291198730469
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9911496913743186
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.74
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.86
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.94
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.74
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.588
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.508
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.07635143960629845
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1800129405239251
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.23739681193828663
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.33976750488378327
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.622759301760137
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8137142857142856
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4830025510651395
            name: Dot Map@100
          - type: query_active_dims
            value: 52.2599983215332
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982877924670227
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 219.79901123046875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9927986694439921
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFEVER
          type: NanoFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.8
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.92
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.94
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.8
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.31999999999999995
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.204
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7566666666666666
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8866666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.92
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.95
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.871923100931238
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8608333333333333
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8427126216077829
            name: Dot Map@100
          - type: query_active_dims
            value: 79.13999938964844
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9974071161984913
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 287.1961669921875
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9905905193961015
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.42
            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: 0.68
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            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: 0.11
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.23607936507936508
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.31813492063492066
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.3794920634920635
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4829047619047619
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.41245963928815416
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4934444444444444
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.35636809652397866
            name: Dot Map@100
          - type: query_active_dims
            value: 54.040000915527344
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982294737921654
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 213.87989807128906
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.992992598844398
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.88
            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: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.88
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5133333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.3399999999999999
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.17199999999999996
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.44
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.77
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.85
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.8259863564109206
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9116666666666667
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.772433308579342
            name: Dot Map@100
          - type: query_active_dims
            value: 68.36000061035156
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9977603040229883
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 223.86521911621094
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9926654472473556
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.9
            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: 0.9
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.38666666666666655
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.24799999999999997
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.12999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.8073333333333333
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.938
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9653333333333333
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.98
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9411045044022702
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9466666666666665
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.9183274196019293
            name: Dot Map@100
          - type: query_active_dims
            value: 57.5
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9981161129676954
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 58.39020919799805
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9980869468187538
            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: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.42
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.28
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.25199999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.154
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08766666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.17266666666666666
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.25766666666666665
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.31566666666666665
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3183178982652113
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5296904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.24557421391176226
            name: Dot Map@100
          - type: query_active_dims
            value: 73.30000305175781
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9975984534744854
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 293.607177734375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9903804738308638
            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: 0.42
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.14
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.13999999999999999
            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: 0.14
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.42
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.58
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.7
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.40946212538272647
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.317547619047619
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3292918677514585
            name: Dot Map@100
          - type: query_active_dims
            value: 281.1600036621094
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.990788283740839
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 268.114990234375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.991215680812713
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.54
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.66
            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: 0.54
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16799999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.092
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.52
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.65
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.74
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.81
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.668993132237426
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.623968253968254
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6278823742890459
            name: Dot Map@100
          - type: query_active_dims
            value: 109.4000015258789
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9964157001007182
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 348.5179748535156
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9885814175069289
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.7346938775510204
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9183673469387755
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9591836734693877
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9591836734693877
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.7346938775510204
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6258503401360545
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5673469387755103
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.4612244897959184
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.052703291471304
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1338383723587515
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.19411388149464573
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.30722833210959427
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5361442152154757
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8255102040816327
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3995866253752792
            name: Dot Map@100
          - type: query_active_dims
            value: 56.61224365234375
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9981451987532814
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 224.8710174560547
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9926324940221462
            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:
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture 

SparseEncoder(
  (0): MLMTransformer({'max_seq_length': 256, 'do_lower_case': False}) with MLMTransformer model: 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/co-condenser-marco-msmarco-hard-negatives")
# Run inference
queries = [
    "fastest super cars in the world",
]
documents = [
    'The McLaren F1 is amongst the fastest cars in the McLaren series and also the fastest car in the world. The McLaren F1 can clock a maximum speed of 240 miles per hour, or an equivalent of 386 km per hour.',
    'You heard about fastest cars, bikes and plans but today we have world fastest bird collection. In our collection we have top 10 fastest birds of the world. Birdâ\x80\x99s flight speed is fundamentally changeable; a hunting bird speed will increase while diving-to-catch prey as compared to its gliding speeds. Here we have the top 10 fastest birds with their flight speed. 10. Teal 109 km/h (68mph) This bird can fly 109 km/ h (68mph); they are 53 to 59cm long. This bird always lives in group. 09.',
    'Where is Langley, BC? Location of Langley on a map. Langley is a city found in British Columbia, Canada. It is located 49.08 latitude and -122.59 longitude and it is situated at elevation 78 meters above sea level. Langley has a population of 93,726 making it the 13th biggest city in British Columbia.',
]
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([[35.7080, 24.5349,  3.8619]])

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 0.4 0.44 0.52 0.32 0.74 0.8 0.42 0.88 0.9 0.42 0.14 0.54 0.7347
dot_accuracy@3 0.62 0.6 0.74 0.52 0.86 0.92 0.52 0.94 1.0 0.56 0.42 0.66 0.9184
dot_accuracy@5 0.68 0.64 0.78 0.54 0.9 0.94 0.58 0.96 1.0 0.74 0.58 0.74 0.9592
dot_accuracy@10 0.84 0.68 0.84 0.62 0.94 0.96 0.68 0.96 1.0 0.78 0.7 0.82 0.9592
dot_precision@1 0.4 0.44 0.52 0.32 0.74 0.8 0.42 0.88 0.9 0.42 0.14 0.54 0.7347
dot_precision@3 0.2067 0.34 0.2533 0.2 0.6133 0.32 0.2133 0.5133 0.3867 0.28 0.14 0.24 0.6259
dot_precision@5 0.136 0.316 0.16 0.14 0.588 0.204 0.168 0.34 0.248 0.252 0.116 0.168 0.5673
dot_precision@10 0.084 0.27 0.09 0.082 0.508 0.106 0.11 0.172 0.13 0.154 0.07 0.092 0.4612
dot_recall@1 0.4 0.0631 0.48 0.165 0.0764 0.7567 0.2361 0.44 0.8073 0.0877 0.14 0.52 0.0527
dot_recall@3 0.62 0.099 0.69 0.26 0.18 0.8867 0.3181 0.77 0.938 0.1727 0.42 0.65 0.1338
dot_recall@5 0.68 0.1169 0.73 0.2873 0.2374 0.92 0.3795 0.85 0.9653 0.2577 0.58 0.74 0.1941
dot_recall@10 0.84 0.1468 0.8 0.3223 0.3398 0.95 0.4829 0.86 0.98 0.3157 0.7 0.81 0.3072
dot_ndcg@10 0.6077 0.3452 0.6595 0.3037 0.6228 0.8719 0.4125 0.826 0.9411 0.3183 0.4095 0.669 0.5361
dot_mrr@10 0.5353 0.5258 0.6369 0.4207 0.8137 0.8608 0.4934 0.9117 0.9467 0.5297 0.3175 0.624 0.8255
dot_map@100 0.5419 0.1699 0.6105 0.2558 0.483 0.8427 0.3564 0.7724 0.9183 0.2456 0.3293 0.6279 0.3996
query_active_dims 54.12 51.7 53.34 135.3 52.26 79.14 54.04 68.36 57.5 73.3 281.16 109.4 56.6122
query_sparsity_ratio 0.9982 0.9983 0.9983 0.9956 0.9983 0.9974 0.9982 0.9978 0.9981 0.9976 0.9908 0.9964 0.9981
corpus_active_dims 187.6754 336.3248 223.5909 270.1291 219.799 287.1962 213.8799 223.8652 58.3902 293.6072 268.115 348.518 224.871
corpus_sparsity_ratio 0.9939 0.989 0.9927 0.9911 0.9928 0.9906 0.993 0.9927 0.9981 0.9904 0.9912 0.9886 0.9926

Sparse Nano BEIR

  • Dataset: NanoBEIR_mean
  • Evaluated with SparseNanoBEIREvaluator with these parameters:
    {
    "dataset_names": [
        "msmarco",
        "nfcorpus",
        "nq"
    ]
}
Metric Value
dot_accuracy@1 0.4533
dot_accuracy@3 0.6533
dot_accuracy@5 0.7
dot_accuracy@10 0.7867
dot_precision@1 0.4533
dot_precision@3 0.2667
dot_precision@5 0.204
dot_precision@10 0.148
dot_recall@1 0.3144
dot_recall@3 0.4697
dot_recall@5 0.509
dot_recall@10 0.5956
dot_ndcg@10 0.5375
dot_mrr@10 0.566
dot_map@100 0.4408
query_active_dims 53.0533
query_sparsity_ratio 0.9983
corpus_active_dims 235.2386
corpus_sparsity_ratio 0.9923

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 0.5581
dot_accuracy@3 0.7137
dot_accuracy@5 0.7722
dot_accuracy@10 0.8292
dot_precision@1 0.5581
dot_precision@3 0.3333
dot_precision@5 0.2618
dot_precision@10 0.1792
dot_recall@1 0.325
dot_recall@3 0.4722
dot_recall@5 0.5337
dot_recall@10 0.6042
dot_ndcg@10 0.5787
dot_mrr@10 0.6494
dot_map@100 0.5041
query_active_dims 86.6795
query_sparsity_ratio 0.9972
corpus_active_dims 230.5676
corpus_sparsity_ratio 0.9924

Training Details

Training Dataset

msmarco

  • Dataset: msmarco at 9e329ed
  • Size: 90,000 training samples
  • Columns: score, query, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    score query positive negative
    type float string string string
    details
    • min: -3.66
    • mean: 12.97
    • max: 22.48
    • min: 4 tokens
    • mean: 8.89 tokens
    • max: 24 tokens
    • min: 16 tokens
    • mean: 80.61 tokens
    • max: 256 tokens
    • min: 18 tokens
    • mean: 78.92 tokens
    • max: 250 tokens
  • Samples:
    score query positive negative
    2.1688317457834883 what is ast test used for The AST test is commonly used to check for liver diseases. It is usually measured together with alanine aminotransferase (ALT). The AST to ALT ratio can help your doctor diagnose liver disease. Symptoms of liver disease that may cause your doctor to order an AST test include: 1 fatigue. 2 weakness.3 loss of appetite.t is usually measured together with alanine aminotransferase (ALT). The AST to ALT ratio can help your doctor diagnose liver disease. Symptoms of liver disease that may cause your doctor to order an AST test include: 1 fatigue. 2 weakness. 3 loss of appetite. An aspartate aminotransferase (AST) test measures the amount of this enzyme in the blood. AST is normally found in red blood cells, liver, heart, muscle tissue, pancreas, and kidneys. AST formerly was called serum glutamic oxaloacetic transaminase (SGOT).he amount of AST in the blood is directly related to the extent of the tissue damage. After severe damage, AST levels rise in 6 to 10 hours and remain high for about 4 days. The AST test may be done at the same time as a test for alanine aminotransferase, or ALT.
    12.405409197012585 what does the suspensory ligament do when the cillary muscles contract Suspensory Ligaments of the Ciliary Body: The suspensory ligaments of the ciliary body are ligaments that attach the ciliary body to the lens of the eye. Suspensory ligaments enable the ciliary body to change the shape of the lens as needed to focus light reflected from objects at different distances from the eye. Ossification of the posterior longitudinal ligament of the spine: Introduction. Ossification of the posterior longitudinal ligament of the spine: Abnormal calcification of a spinal ligament. The progressive calcification can starts within months of birth and affects the ability to move arms and legs.ssification of the posterior longitudinal ligament of the spine: Introduction. Ossification of the posterior longitudinal ligament of the spine: Abnormal calcification of a spinal ligament. The progressive calcification can starts within months of birth and affects the ability to move arms and legs.
    19.407212177912392 how many kids does trump have Donald Trump has 5 children: Donald Jr., Eric, and Ivanka- mother Ivana Trump Tiffany -mother Marla Maples Barron-mother Malania Trump Donald Trump Jr. has 2 children: … Kai Madison Trump and Donald Trump III. Copyright © 2018, Trump Make America Great Again Committee. Paid for by Trump Make America Great Again Committee, a joint fundraising committee authorized by and composed of Donald J. Trump for President, Inc. and the Republican National Committee. x Close
  • Loss: SpladeLoss with these parameters:
    {
    "loss": "SparseMarginMSELoss",
    "lambda_corpus": 0.08,
    "lambda_query": 0.1
}

Evaluation Dataset

msmarco

  • Dataset: msmarco at 9e329ed
  • Size: 10,000 evaluation samples
  • Columns: score, query, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    score query positive negative
    type float string string string
    details
    • min: -4.07
    • mean: 13.12
    • max: 22.25
    • min: 4 tokens
    • mean: 8.96 tokens
    • max: 33 tokens
    • min: 13 tokens
    • mean: 80.54 tokens
    • max: 220 tokens
    • min: 17 tokens
    • mean: 78.41 tokens
    • max: 242 tokens
  • Samples:
    score query positive negative
    11.227776050567627 tabernacle definition Wiktionary(0.00 / 0 votes)Rate this definition: tabernacle(Noun) any temporary dwelling, a hut, tent, booth. tabernacle(Noun) (Old Testament) The portable tent used before the construction of the temple, where the shekinah (presence of God) was believed to dwell. 1611 ... So Moses finished the work. Then a cloud covered the tent of the congregation, and the glory of the LORD filled the tabernacle. Both the Annunciation tabernacle in Santa Croce and the Cantoria (the singer's pulpit) in the Duomo (now in the Museo dell'Opera del Duomo) show a vastly increased repertory of forms derived from ancient art, the harvest of Donatello's long stay in Rome (1430-33).
    12.354041655858357 what scientist discovered radiation Becquerel used an apparatus similar to that displayed below to show that the radiation he discovered could not be x-rays. X-rays are neutral and cannot be bent in a magnetic field. The new radiation was bent by the magnetic field so that the radiation must be charged and different than x-rays. 5a-Hydroxy Laxogenin. 5a-Hydroxy Laxogenin was discovered by a American scientist in 1996. It was shown to possess an anabolic/androgenic ratio similar to one of the most efficient anabolic substances, in particular Anavar but without the side effects of liver toxicity or testing positive for steroidal therapy.
    11.721514344215393 are horses primates Primates still do, but many, if not most, mammals do not. Horses, deer, cows and many other mammals have a reduced number of digits on their forelimbs and hindlimbs. Primates also retain other generalized skeletal features like the clavicle or collar bone. The only primates that live in Canada are humans. The species originated in east Africa and is unrelated to South American primates. Humans first arrived in large numbers to Canada around 15,000 years ago from North Asia, and surged in migration starting 400 years ago from around the world, especially from Europe.
  • Loss: SpladeLoss with these parameters:
    {
    "loss": "SparseMarginMSELoss",
    "lambda_corpus": 0.08,
    "lambda_query": 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}
  • tp_size: 0
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: None
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • include_for_metrics: []
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • 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: 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 664548.88 - - - - - - - - - - - - - - -
0.0356 200 1912.7461 - - - - - - - - - - - - - - -
0.0533 300 89.4823 - - - - - - - - - - - - - - -
0.0711 400 57.4213 - - - - - - - - - - - - - - -
0.0889 500 43.5322 37.8169 0.5271 0.2411 0.5761 0.4481 - - - - - - - - - -
0.1067 600 38.8042 - - - - - - - - - - - - - - -
0.1244 700 34.1112 - - - - - - - - - - - - - - -
0.1422 800 30.3487 - - - - - - - - - - - - - - -
0.16 900 30.4368 - - - - - - - - - - - - - - -
0.1778 1000 30.9444 27.4550 0.5513 0.3375 0.6122 0.5003 - - - - - - - - - -
0.1956 1100 27.7082 - - - - - - - - - - - - - - -
0.2133 1200 28.6251 - - - - - - - - - - - - - - -
0.2311 1300 27.6298 - - - - - - - - - - - - - - -
0.2489 1400 24.1523 - - - - - - - - - - - - - - -
0.2667 1500 25.3053 23.4952 0.5898 0.3416 0.6296 0.5203 - - - - - - - - - -
0.2844 1600 24.8645 - - - - - - - - - - - - - - -
0.3022 1700 25.9037 - - - - - - - - - - - - - - -
0.32 1800 25.255 - - - - - - - - - - - - - - -
0.3378 1900 24.4475 - - - - - - - - - - - - - - -
0.3556 2000 22.8183 26.7798 0.5579 0.3407 0.6160 0.5049 - - - - - - - - - -
0.3733 2100 22.0948 - - - - - - - - - - - - - - -
0.3911 2200 22.9483 - - - - - - - - - - - - - - -
0.4089 2300 20.8408 - - - - - - - - - - - - - - -
0.4267 2400 19.5543 - - - - - - - - - - - - - - -
0.4444 2500 20.9379 18.6976 0.6327 0.3216 0.6255 0.5266 - - - - - - - - - -
0.4622 2600 20.2078 - - - - - - - - - - - - - - -
0.48 2700 20.6449 - - - - - - - - - - - - - - -
0.4978 2800 19.1764 - - - - - - - - - - - - - - -
0.5156 2900 19.4603 - - - - - - - - - - - - - - -
0.5333 3000 20.3068 18.4043 0.6081 0.3220 0.6515 0.5272 - - - - - - - - - -
0.5511 3100 19.1402 - - - - - - - - - - - - - - -
0.5689 3200 18.0542 - - - - - - - - - - - - - - -
0.5867 3300 17.9658 - - - - - - - - - - - - - - -
0.6044 3400 18.4345 - - - - - - - - - - - - - - -
0.6222 3500 19.4609 17.0769 0.6155 0.3219 0.6545 0.5306 - - - - - - - - - -
0.64 3600 17.4228 - - - - - - - - - - - - - - -
0.6578 3700 17.8939 - - - - - - - - - - - - - - -
0.6756 3800 16.2358 - - - - - - - - - - - - - - -
0.6933 3900 16.6908 - - - - - - - - - - - - - - -
0.7111 4000 15.9995 17.7298 0.6022 0.3555 0.6525 0.5367 - - - - - - - - - -
0.7289 4100 16.3495 - - - - - - - - - - - - - - -
0.7467 4200 15.559 - - - - - - - - - - - - - - -
0.7644 4300 17.4544 - - - - - - - - - - - - - - -
0.7822 4400 15.8666 - - - - - - - - - - - - - - -
0.8 4500 16.3616 18.8307 0.6036 0.3472 0.6112 0.5207 - - - - - - - - - -
0.8178 4600 15.276 - - - - - - - - - - - - - - -
0.8356 4700 15.2697 - - - - - - - - - - - - - - -
0.8533 4800 16.6727 - - - - - - - - - - - - - - -
0.8711 4900 15.2223 - - - - - - - - - - - - - - -
0.8889 5000 15.7583 16.2949 0.6177 0.3438 0.6505 0.5373 - - - - - - - - - -
0.9067 5100 15.3164 - - - - - - - - - - - - - - -
0.9244 5200 14.9429 - - - - - - - - - - - - - - -
0.9422 5300 15.5992 - - - - - - - - - - - - - - -
0.96 5400 14.8593 - - - - - - - - - - - - - - -
0.9778 5500 14.7565 16.423 0.6077 0.3452 0.6595 0.5375 - - - - - - - - - -
0.9956 5600 14.5115 - - - - - - - - - - - - - - -
-1 -1 - - 0.6077 0.3452 0.6595 0.5787 0.3037 0.6228 0.8719 0.4125 0.8260 0.9411 0.3183 0.4095 0.6690 0.5361
  • The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

  • Energy Consumed: 0.093 kWh
  • Carbon Emitted: 0.034 kg of CO2
  • Hours Used: 0.305 hours

Training Hardware

  • On Cloud: No
  • GPU Model: 1 x NVIDIA H100 80GB HBM3
  • CPU Model: AMD EPYC 7R13 Processor
  • RAM Size: 248.00 GB

Framework Versions

  • Python: 3.13.3
  • Sentence Transformers: 4.2.0.dev0
  • Transformers: 4.51.3
  • PyTorch: 2.7.1+cu126
  • Accelerate: 0.26.0
  • 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},
}

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}
    }