metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sparse-encoder
  - sparse
  - splade
  - generated_from_trainer
  - dataset_size:90000
  - loss:SpladeLoss
  - loss:SparseMultipleNegativesRankingLoss
  - loss:FlopsLoss
base_model: distilbert/distilbert-base-uncased
widget:
  - text: yvette mimieux net worth
  - text: is sweet potato fries a bad calorie for you
  - text: >-
      The name Gunnar is a Swedish baby name. In Swedish the meaning of the name
      Gunnar is: Battle strong. American Meaning: The name Gunnar is an American
      baby name.In American the meaning of the name Gunnar is: Battle
      strong.Teutonic Meaning: The name Gunnar is a Teutonic baby name.In
      Teutonic the meaning of the name Gunnar is: Bold warrior. Norse Meaning:
      The name Gunnar is a Norse baby name. In Norse the meaning of the name
      Gunnar is: Iighter. Scandinavian Meaning: The name Gunnar is a
      Scandinavian baby name.he name Gunnar is a Teutonic baby name. In Teutonic
      the meaning of the name Gunnar is: Bold warrior. Norse Meaning: The name
      Gunnar is a Norse baby name. In Norse the meaning of the name Gunnar is:
      Iighter. Scandinavian Meaning: The name Gunnar is a Scandinavian baby
      name.
  - text: what your fsh test results indicate
  - text: >-
      1 Lymphoma, the most common canine cancer, usually requires only
      chemotherapy and its cost can come up to be around $450 to $500. 2 
      Osteosarcoma, another type of canine cancer, is usually treated with
      chemotherapy along with amputation surgery.3  This type of chemotherapy
      treatment costs approximately $450.nother factor is the type of drugs used
      in the process. The size of the dog that needs to undergo chemotherapy can
      also impact the cost. Even a dog very small in size with a single
      cancerous lesion can cost $200 for chemotherapy, while the same problem on
      a larger breed could cost more than $1,000 a month.
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: 53.738116037369885
  energy_consumed: 0.1382501660330276
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.458
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: splade-distilbert-base-uncased trained on MS MARCO triplets
    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: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            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: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            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: 0.72
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6227350359947015
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5469285714285713
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5547419639747225
            name: Dot Map@100
          - type: query_active_dims
            value: 23.6200008392334
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999226131942886
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 86.9286117553711
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9971519359230925
            name: Corpus Sparsity Ratio
          - 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: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.86
            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: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            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: 0.72
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6227350359947015
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5469285714285713
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.5547419639747225
            name: Dot Map@100
          - type: query_active_dims
            value: 23.6200008392334
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999226131942886
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 86.9286117553711
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9971519359230925
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoNFCorpus
          type: NanoNFCorpus
        metrics:
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.36666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.266
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.021751342131059177
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07406240621283516
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09358105221669372
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.11969365467146144
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3145066096009473
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4676904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1297946574794519
            name: Dot Map@100
          - type: query_active_dims
            value: 18.780000686645508
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9993847060911262
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 164.79444885253906
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9946007978227986
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.38
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.58
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.62
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.38
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.36666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.32799999999999996
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.266
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.021751342131059177
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.07406240621283516
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.09358105221669372
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.11969365467146144
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.3145066096009473
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.4676904761904762
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.1297946574794519
            name: Dot Map@100
          - type: query_active_dims
            value: 18.780000686645508
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9993847060911262
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 164.79444885253906
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9946007978227986
            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: 0.7
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.52
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.75
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6400441027431699
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6203571428571428
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6045362504066882
            name: Dot Map@100
          - type: query_active_dims
            value: 26.940000534057617
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999117357953802
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 109.75908660888672
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.99640393530539
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.52
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.7
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.72
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.52
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.14400000000000002
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08199999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.5
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.66
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.68
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.75
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6400441027431699
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6203571428571428
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6045362504066882
            name: Dot Map@100
          - type: query_active_dims
            value: 26.940000534057617
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999117357953802
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 109.75908660888672
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.99640393530539
            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: 0.4266666666666667
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6333333333333334
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6733333333333332
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7533333333333333
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4266666666666667
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.20533333333333334
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.14466666666666664
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3005837807103531
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.46468746873761174
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.49786035073889795
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.5765645515571538
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5257619161129395
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5449920634920634
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4296909572869542
            name: Dot Map@100
          - type: query_active_dims
            value: 23.11333401997884
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9992427319959382
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 113.39544145649826
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9962847964924808
            name: Corpus Sparsity Ratio
          - type: dot_accuracy@1
            value: 0.531773940345369
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.6966718995290424
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.7506122448979593
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.8230455259026688
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.531773940345369
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3291470434327577
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.25535321821036105
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.18231397174254316
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.3098648701114875
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.4649217800565723
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.5185635370811593
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.6012619916233037
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.570153816546152
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6274141187610573
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.49205810209697926
            name: Dot Map@100
          - type: query_active_dims
            value: 40.89984672205474
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9986599879849926
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 112.74959253323884
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9963059566039827
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoClimateFEVER
          type: NanoClimateFEVER
        metrics:
          - type: dot_accuracy@1
            value: 0.26
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.46
            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: 0.26
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.16
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.124
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.094
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.13166666666666665
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.22899999999999998
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.26966666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3686666666666667
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.29349270164622415
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.3810238095238095
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.22256540249654586
            name: Dot Map@100
          - type: query_active_dims
            value: 52.70000076293945
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982733765558306
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 152.81748962402344
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9949932019650081
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoDBPedia
          type: NanoDBPedia
        metrics:
          - type: dot_accuracy@1
            value: 0.76
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.88
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.88
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.76
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6066666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5840000000000001
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.514
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.08858465342637668
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.17454996352915306
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.2491328586940767
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.358206868666866
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.632129041524978
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8133333333333332
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.490256496112331
            name: Dot Map@100
          - type: query_active_dims
            value: 22.979999542236328
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9992471004671307
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 103.23821258544922
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9966175803490777
            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: 0.9
            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: 0.8
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.30666666666666664
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.204
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10399999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7666666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8666666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9333333333333332
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9433333333333332
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.8746461544855423
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8663333333333334
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8475954415954416
            name: Dot Map@100
          - type: query_active_dims
            value: 41.619998931884766
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9986363934561338
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 154.98318481445312
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9949222467461355
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoFiQA2018
          type: NanoFiQA2018
        metrics:
          - type: dot_accuracy@1
            value: 0.32
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.54
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.6
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.7
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.32
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.24
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.172
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.10599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.1620793650793651
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.36180158730158724
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.4036349206349206
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.4941031746031746
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.38562756897614053
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.43427777777777765
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3209789709019607
            name: Dot Map@100
          - type: query_active_dims
            value: 22.68000030517578
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9992569294179551
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 89.73922729492188
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9970598510158272
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoHotpotQA
          type: NanoHotpotQA
        metrics:
          - type: dot_accuracy@1
            value: 0.9
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.96
            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: 0.9
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.5199999999999999
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.324
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.172
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.45
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.78
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.81
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.86
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.8341414369684795
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9266666666666665
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.7830202707785705
            name: Dot Map@100
          - type: query_active_dims
            value: 43.13999938964844
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9985865932969776
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 108.24322509765625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9964535998591949
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoQuoraRetrieval
          type: NanoQuoraRetrieval
        metrics:
          - type: dot_accuracy@1
            value: 0.84
            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: 0.96
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.84
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.35999999999999993
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.22399999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.12199999999999997
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.774
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8853333333333333
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.902
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.93
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.891220122907666
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8916666666666666
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8739838721281753
            name: Dot Map@100
          - type: query_active_dims
            value: 21.780000686645508
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.999286416332919
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 24.841062545776367
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9991861259895886
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSCIDOCS
          type: NanoSCIDOCS
        metrics:
          - type: dot_accuracy@1
            value: 0.44
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.56
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.62
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.76
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.44
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2733333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.22399999999999998
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.162
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.09266666666666667
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1696666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.22966666666666669
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.3306666666666666
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.32673772222029135
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.5299920634920635
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.24677603468739176
            name: Dot Map@100
          - type: query_active_dims
            value: 40.18000030517578
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9986835724950798
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 145.2197265625
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.995242129396419
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoArguAna
          type: NanoArguAna
        metrics:
          - type: dot_accuracy@1
            value: 0.12
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.44
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.54
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.72
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.12
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.14666666666666667
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.10800000000000003
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.07200000000000001
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.12
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.44
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.54
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.72
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.40190838047249483
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.30241269841269836
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.3152551920928219
            name: Dot Map@100
          - type: query_active_dims
            value: 142.10000610351562
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9953443415862815
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 133.527099609375
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.995625217888429
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoSciFact
          type: NanoSciFact
        metrics:
          - type: dot_accuracy@1
            value: 0.54
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.64
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.74
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.78
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.54
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.2333333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.16
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.08599999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.495
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.615
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.715
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.76
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.6395168665161247
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6164444444444444
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6051482940863745
            name: Dot Map@100
          - type: query_active_dims
            value: 54.2400016784668
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9982229211166219
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 172.6594696044922
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9943431141601305
            name: Corpus Sparsity Ratio
      - task:
          type: sparse-information-retrieval
          name: Sparse Information Retrieval
        dataset:
          name: NanoTouche2020
          type: NanoTouche2020
        metrics:
          - type: dot_accuracy@1
            value: 0.6530612244897959
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8367346938775511
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.8979591836734694
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9795918367346939
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.6530612244897959
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.6122448979591837
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.5795918367346938
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.5040816326530612
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.045827950812536176
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.1279025170251966
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.19531048384271374
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.32173552649478127
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.5552938710432158
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.7592565597667638
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.4021024805202534
            name: Dot Map@100
          - type: query_active_dims
            value: 20.53061294555664
            name: Query Active Dims
          - type: query_sparsity_ratio
            value: 0.9993273503392452
            name: Query Sparsity Ratio
          - type: corpus_active_dims
            value: 106.17720031738281
            name: Corpus Active Dims
          - type: corpus_sparsity_ratio
            value: 0.9965212895512292
            name: Corpus Sparsity Ratio

splade-distilbert-base-uncased trained on MS MARCO triplets

This is a SPLADE Sparse Encoder model finetuned from distilbert/distilbert-base-uncased 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: distilbert/distilbert-base-uncased
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}) with MLMTransformer model: DistilBertForMaskedLM 
  (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/splade-distilbert-base-uncased-msmarco-mnrl")
# Run inference
queries = [
    "canine ultrasound cost",
]
documents = [
    'VetInfo indicates that any type of canine ultrasound costs anywhere from $300 to $500 depending on what region of the country you live in and whether or not a veterinarian or a technician performs the procedure.',
    '1 Lymphoma, the most common canine cancer, usually requires only chemotherapy and its cost can come up to be around $450 to $500. 2  Osteosarcoma, another type of canine cancer, is usually treated with chemotherapy along with amputation surgery.3  This type of chemotherapy treatment costs approximately $450.nother factor is the type of drugs used in the process. The size of the dog that needs to undergo chemotherapy can also impact the cost. Even a dog very small in size with a single cancerous lesion can cost $200 for chemotherapy, while the same problem on a larger breed could cost more than $1,000 a month.',
    'Plant Life. There are many different plants in the rain forest. Some of the plants include vines, bromeliads, the passion fruit plant and the Victorian water lily. Vines in the rainforest can be as thick as the average human average human body and some can grow to be 3,000 ft long.',
]
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([[33.7473, 25.6638,  0.2965]])

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	0.38	0.52	0.26	0.76	0.8	0.32	0.9	0.84	0.44	0.12	0.54	0.6531
dot_accuracy@3	0.66	0.54	0.7	0.46	0.88	0.9	0.54	0.96	0.94	0.56	0.44	0.64	0.8367
dot_accuracy@5	0.72	0.58	0.72	0.58	0.88	0.96	0.6	0.96	0.96	0.62	0.54	0.74	0.898
dot_accuracy@10	0.86	0.62	0.78	0.7	0.9	0.98	0.7	0.96	0.96	0.76	0.72	0.78	0.9796
dot_precision@1	0.38	0.38	0.52	0.26	0.76	0.8	0.32	0.9	0.84	0.44	0.12	0.54	0.6531
dot_precision@3	0.22	0.3667	0.2333	0.16	0.6067	0.3067	0.24	0.52	0.36	0.2733	0.1467	0.2333	0.6122
dot_precision@5	0.144	0.328	0.144	0.124	0.584	0.204	0.172	0.324	0.224	0.224	0.108	0.16	0.5796
dot_precision@10	0.086	0.266	0.082	0.094	0.514	0.104	0.106	0.172	0.122	0.162	0.072	0.086	0.5041
dot_recall@1	0.38	0.0218	0.5	0.1317	0.0886	0.7667	0.1621	0.45	0.774	0.0927	0.12	0.495	0.0458
dot_recall@3	0.66	0.0741	0.66	0.229	0.1745	0.8667	0.3618	0.78	0.8853	0.1697	0.44	0.615	0.1279
dot_recall@5	0.72	0.0936	0.68	0.2697	0.2491	0.9333	0.4036	0.81	0.902	0.2297	0.54	0.715	0.1953
dot_recall@10	0.86	0.1197	0.75	0.3687	0.3582	0.9433	0.4941	0.86	0.93	0.3307	0.72	0.76	0.3217
dot_ndcg@10	0.6227	0.3145	0.64	0.2935	0.6321	0.8746	0.3856	0.8341	0.8912	0.3267	0.4019	0.6395	0.5553
dot_mrr@10	0.5469	0.4677	0.6204	0.381	0.8133	0.8663	0.4343	0.9267	0.8917	0.53	0.3024	0.6164	0.7593
dot_map@100	0.5547	0.1298	0.6045	0.2226	0.4903	0.8476	0.321	0.783	0.874	0.2468	0.3153	0.6051	0.4021
query_active_dims	23.62	18.78	26.94	52.7	22.98	41.62	22.68	43.14	21.78	40.18	142.1	54.24	20.5306
query_sparsity_ratio	0.9992	0.9994	0.9991	0.9983	0.9992	0.9986	0.9993	0.9986	0.9993	0.9987	0.9953	0.9982	0.9993
corpus_active_dims	86.9286	164.7944	109.7591	152.8175	103.2382	154.9832	89.7392	108.2432	24.8411	145.2197	133.5271	172.6595	106.1772
corpus_sparsity_ratio	0.9972	0.9946	0.9964	0.995	0.9966	0.9949	0.9971	0.9965	0.9992	0.9952	0.9956	0.9943	0.9965

Sparse Nano BEIR

Dataset: NanoBEIR_mean

Evaluated with SparseNanoBEIREvaluator with these parameters:

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

Metric	Value
dot_accuracy@1	0.4267
dot_accuracy@3	0.6333
dot_accuracy@5	0.6733
dot_accuracy@10	0.7533
dot_precision@1	0.4267
dot_precision@3	0.2733
dot_precision@5	0.2053
dot_precision@10	0.1447
dot_recall@1	0.3006
dot_recall@3	0.4647
dot_recall@5	0.4979
dot_recall@10	0.5766
dot_ndcg@10	0.5258
dot_mrr@10	0.545
dot_map@100	0.4297
query_active_dims	23.1133
query_sparsity_ratio	0.9992
corpus_active_dims	113.3954
corpus_sparsity_ratio	0.9963

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	0.5318
dot_accuracy@3	0.6967
dot_accuracy@5	0.7506
dot_accuracy@10	0.823
dot_precision@1	0.5318
dot_precision@3	0.3291
dot_precision@5	0.2554
dot_precision@10	0.1823
dot_recall@1	0.3099
dot_recall@3	0.4649
dot_recall@5	0.5186
dot_recall@10	0.6013
dot_ndcg@10	0.5702
dot_mrr@10	0.6274
dot_map@100	0.4921
query_active_dims	40.8998
query_sparsity_ratio	0.9987
corpus_active_dims	112.7496
corpus_sparsity_ratio	0.9963

Training Details

Training Dataset

msmarco

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

Approximate statistics based on the first 1000 samples:

	query	positive	negative
type	string	string	string
details	min: 4 tokens mean: 9.1 tokens max: 30 tokens	min: 24 tokens mean: 79.91 tokens max: 218 tokens	min: 22 tokens mean: 77.09 tokens max: 256 tokens

Samples:

query	positive	negative
`when do manga complete editions`	`Volumes 9 and 10 the Sailor Moon Manga Complete Editions are now out. Last week, March 25th, volumes 9 and 10 of the Sailor Moon Manga Complete Editions were released in Japan. Volume 9 features Endymion and Serenity on the cover while volume 10 features all 10 Sailor Guardians.`	`Destiny: The Taken King will be released in standard download, collectorâs edition download, and both âCollectorâsâ and âLegendaryâ game disc editions on September 15, 2015.`
`the define of homograph`	`LINK / CITE ADD TO WORD LIST. noun. The definition of a homograph is a word that is spelled like another word or other words, but has a different meaning and sometimes sounds different. An example of a homograph is evening, which is the time of day after the sun has set or making something level or flat.`	`As verbs the difference between describe and define. is that describe is to represent in words while define is to determine. As a noun define is. (computing`
`what is a cv in resume writing`	`Curriculum Vitae (CV) is Latin for âcourse of life.â In contrast, resume is French for âsummary.â Both CVs & Resumes: 1 Are tailored for the specific job/company you are applying to. 2 Should represent you as the best qualified candidate. 3 Are used to get you an interview. Do not usually include personal interests.`	`Resume Samples Â» Resume Objective Â» Legal Resume Objective Â» Legal Assistant Resume Objective. Job Description: Legal assistant is responsible to manage and handle various activities of legal department. Preparing legal documents such as contracts, wills and appeals.`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
    "lambda_corpus": 0.001,
    "lambda_query": 5e-05
}

Evaluation Dataset

msmarco

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

Approximate statistics based on the first 1000 samples:

	query	positive	negative
type	string	string	string
details	min: 5 tokens mean: 9.24 tokens max: 53 tokens	min: 13 tokens mean: 80.9 tokens max: 204 tokens	min: 17 tokens mean: 78.24 tokens max: 234 tokens

Samples:

query	positive	negative
`the largest vietnamese population in the united states is in`	`The largest number of Vietnamese outside Vietnam is in Orange County, California (184,153, or 6.1 percent of the county's population), followed by Los Angeles and Santa Clara counties; the three counties accounted for 26 percent of the Vietnamese immigrant population in the United States.`	`Population by Place in the United States There are 29,257 places in the United States. This section compares Hibbing to the 50 most populous places in the United States. The least populous of the compared places has a population of 371,267.`
`how many calories in a tablespoon of flaxseed`	`Calorie Content. A 2-tablespoon serving of ground flaxseed has about 75 calories, according to the U.S. Department of Agriculture. These calories consist of 2.6 grams of protein, 4 grams of carbohydrates -- almost all of which is fiber -- and 6 grams of fat.`	`You can also use flaxseed meal to replace an egg. Use 1 tablespoon flaxseed meal and 3 tablespoons water. You can replace up to two eggs in a recipe in this manner, but do not use flaxseed meal as an egg replacement if you are already using it as an oil replacement. Flaxseed has many health benefits.`
`who wrote the house of seven gables`	`The author of The House Of Seven Gables is Nathaniel Hawthorne.`	`Abigail Adams Wrote To John In 1776: Remember The Ladies Or We'll Rebel Adams wrote a feminist letter to her husband just before U.S. independence.`

Loss: SpladeLoss with these parameters:

{
    "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
    "lambda_corpus": 0.001,
    "lambda_query": 5e-05
}

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
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 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
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	NanoMSMARCO_dot_ndcg@10	NanoNFCorpus_dot_ndcg@10	NanoNQ_dot_ndcg@10	NanoBEIR_mean_dot_ndcg@10	NanoClimateFEVER_dot_ndcg@10	NanoDBPedia_dot_ndcg@10	NanoFEVER_dot_ndcg@10	NanoFiQA2018_dot_ndcg@10	NanoHotpotQA_dot_ndcg@10	NanoQuoraRetrieval_dot_ndcg@10	NanoSCIDOCS_dot_ndcg@10	NanoArguAna_dot_ndcg@10	NanoSciFact_dot_ndcg@10	NanoTouche2020_dot_ndcg@10
0.0178	100	173.8874	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0356	200	11.8803	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0533	300	1.0264	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0711	400	0.3923	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.0889	500	0.32	0.2369	0.4932	0.3001	0.5819	0.4584	-	-	-	-	-	-	-	-	-	-
0.1067	600	0.2483	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1244	700	0.28	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1422	800	0.2095	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.16	900	0.2093	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.1778	1000	0.1636	0.1898	0.6051	0.2845	0.6124	0.5006	-	-	-	-	-	-	-	-	-	-
0.1956	1100	0.1661	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2133	1200	0.1964	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2311	1300	0.1937	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2489	1400	0.1771	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.2667	1500	0.1643	0.1549	0.5868	0.3176	0.5769	0.4938	-	-	-	-	-	-	-	-	-	-
0.2844	1600	0.1987	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3022	1700	0.178	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.32	1800	0.1227	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3378	1900	0.1478	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3556	2000	0.1502	0.1563	0.6249	0.3309	0.6088	0.5215	-	-	-	-	-	-	-	-	-	-
0.3733	2100	0.1623	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.3911	2200	0.1703	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4089	2300	0.1804	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4267	2400	0.121	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4444	2500	0.1451	0.1325	0.5620	0.3233	0.6197	0.5017	-	-	-	-	-	-	-	-	-	-
0.4622	2600	0.1609	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.48	2700	0.1415	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.4978	2800	0.1555	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5156	2900	0.1581	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5333	3000	0.1351	0.1546	0.5901	0.3187	0.6299	0.5129	-	-	-	-	-	-	-	-	-	-
0.5511	3100	0.1308	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5689	3200	0.1313	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.5867	3300	0.1248	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6044	3400	0.1295	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6222	3500	0.1398	0.1449	0.6096	0.3285	0.5975	0.5119	-	-	-	-	-	-	-	-	-	-
0.64	3600	0.1105	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6578	3700	0.0911	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6756	3800	0.1683	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.6933	3900	0.1202	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7111	4000	0.135	0.1592	0.5989	0.3109	0.6460	0.5186	-	-	-	-	-	-	-	-	-	-
0.7289	4100	0.1205	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7467	4200	0.1432	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7644	4300	0.105	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.7822	4400	0.1028	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8	4500	0.1386	0.1383	0.5859	0.3084	0.6276	0.5073	-	-	-	-	-	-	-	-	-	-
0.8178	4600	0.1068	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8356	4700	0.1262	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8533	4800	0.1182	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8711	4900	0.1331	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.8889	5000	0.1436	0.1279	0.6261	0.3136	0.6314	0.5237	-	-	-	-	-	-	-	-	-	-
0.9067	5100	0.1182	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9244	5200	0.1379	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9422	5300	0.1343	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.96	5400	0.1475	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
0.9778	5500	0.0988	0.1311	0.6227	0.3145	0.64	0.5258	-	-	-	-	-	-	-	-	-	-
0.9956	5600	0.1072	-	-	-	-	-	-	-	-	-	-	-	-	-	-	-
-1	-1	-	-	0.6227	0.3145	0.6400	0.5702	0.2935	0.6321	0.8746	0.3856	0.8341	0.8912	0.3267	0.4019	0.6395	0.5553

The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.138 kWh
Carbon Emitted: 0.054 kg of CO2
Hours Used: 0.458 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 4.2.0.dev0
Transformers: 4.52.4
PyTorch: 2.7.1+cu126
Accelerate: 1.5.1
Datasets: 2.21.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

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

SpladeLoss

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

SparseMultipleNegativesRankingLoss

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

FlopsLoss

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