checkpoint-1800/README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:124788
  - loss:GISTEmbedLoss
base_model: BAAI/bge-small-en-v1.5
widget:
  - source_sentence: 其他机械、设备和有形货物租赁服务代表
    sentences:
      - 其他机械和设备租赁服务工作人员
      - 电子和电信设备及零部件物流经理
      - 工业主厨
  - source_sentence: 公交车司机
    sentences:
      - 表演灯光设计师
      - 乙烯基地板安装工
      - 国际巴士司机
  - source_sentence: online communication manager
    sentences:
      - trades union official
      - social media manager
      - budget manager
  - source_sentence: Projektmanagerin
    sentences:
      - Projektmanager/Projektmanagerin
      - Category-Manager
      - Infanterist
  - source_sentence: Volksvertreter
    sentences:
      - Parlamentarier
      - Oberbürgermeister
      - Konsul
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@20
  - cosine_accuracy@50
  - cosine_accuracy@100
  - cosine_accuracy@150
  - cosine_accuracy@200
  - cosine_precision@1
  - cosine_precision@20
  - cosine_precision@50
  - cosine_precision@100
  - cosine_precision@150
  - cosine_precision@200
  - cosine_recall@1
  - cosine_recall@20
  - cosine_recall@50
  - cosine_recall@100
  - cosine_recall@150
  - cosine_recall@200
  - cosine_ndcg@1
  - cosine_ndcg@20
  - cosine_ndcg@50
  - cosine_ndcg@100
  - cosine_ndcg@150
  - cosine_ndcg@200
  - cosine_mrr@1
  - cosine_mrr@20
  - cosine_mrr@50
  - cosine_mrr@100
  - cosine_mrr@150
  - cosine_mrr@200
  - cosine_map@1
  - cosine_map@20
  - cosine_map@50
  - cosine_map@100
  - cosine_map@150
  - cosine_map@200
  - cosine_map@500
model-index:
  - name: SentenceTransformer based on BAAI/bge-small-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full en
          type: full_en
        metrics:
          - type: cosine_accuracy@1
            value: 0.6571428571428571
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.9904761904761905
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.9904761904761905
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.9904761904761905
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.9904761904761905
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9904761904761905
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.6571428571428571
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.5076190476190475
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.3089523809523809
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.1872380952380952
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.1321904761904762
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.1027142857142857
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.0680237860830842
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.5459242543214992
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.728483344815942
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.8382149119179341
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.8762032488748317
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.9059964336434017
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.6571428571428571
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.6895375515490911
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.7060633068166344
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.7619501692018719
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.778798440383198
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.7899830993214225
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.6571428571428571
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.8098412698412698
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.8098412698412698
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.8098412698412698
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.8098412698412698
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.8098412698412698
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.6571428571428571
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.5464916843297755
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.5351890636433139
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.5685440196941911
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.5756567539581475
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.5791635361565666
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.5835322146366259
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full es
          type: full_es
        metrics:
          - type: cosine_accuracy@1
            value: 0.12432432432432433
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 1
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 1
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 1
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 1
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 1
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.12432432432432433
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.4924324324324324
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.31686486486486487
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.19843243243243244
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.14702702702702705
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.11762162162162161
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.003111544931768446
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.3235933309332048
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.4622883553307717
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.5424114301447981
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.5822792579944903
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.612586126212026
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.12432432432432433
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.5406828319866788
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.500776817925352
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.5143442473922782
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.5349751306205418
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.5498255219419508
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.12432432432432433
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.5516816816816817
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.5516816816816817
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.5516816816816817
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.5516816816816817
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.5516816816816817
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.12432432432432433
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.4061591888137979
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.3426196432849601
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.3398108870028267
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.3482007813358776
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.3534583367060008
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.36353547903357536
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full de
          type: full_de
        metrics:
          - type: cosine_accuracy@1
            value: 0.2955665024630542
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.9211822660098522
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.9605911330049262
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.9753694581280788
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.9852216748768473
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9852216748768473
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.2955665024630542
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.4226600985221674
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.2775369458128079
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.1787192118226601
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.1349753694581281
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.10960591133004927
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.01108543831680986
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.25787568646307335
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.378544115518205
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.4646991741198787
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.514077820298434
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.5479242719935129
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.2955665024630542
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.4571806408684656
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.4186161244795668
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.43413691996468995
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.45936827865079527
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.4762742892652946
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.2955665024630542
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.488501497777794
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.48978270334574775
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.4900376562912742
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.4901135143922775
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.4901135143922775
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.2955665024630542
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.3211048669539684
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.261888445835493
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.2558901722323677
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.2649913870834412
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.27010541031599244
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.28106938786931224
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full zh
          type: full_zh
        metrics:
          - type: cosine_accuracy@1
            value: 0.30097087378640774
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.7087378640776699
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.8252427184466019
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.8543689320388349
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.912621359223301
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.941747572815534
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.30097087378640774
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.16844660194174763
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.09436893203883494
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.05844660194174757
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.04601941747572815
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.038203883495145634
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.024446152054452382
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.17513112391433697
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.23948897590045773
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.2859906000645493
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.32910264724851107
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.36304017348331746
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.30097087378640774
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.23848199480652515
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.23417872356945213
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.2558557487315817
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.27344459654855646
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.28574499658549296
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.30097087378640774
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.4211010881954553
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.4249525777196882
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.42539460155740233
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.42587488715939736
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.4260266850474542
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.30097087378640774
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.14164601531439067
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.12333195286802508
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.12884550949445583
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.13149151347084506
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.1329204280861929
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.13684460640814028
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix es
          type: mix_es
        metrics:
          - type: cosine_accuracy@1
            value: 0.40717628705148207
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.7581903276131046
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.8455538221528861
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.9048361934477379
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.9370774830993239
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9547581903276131
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.40717628705148207
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.08819552782111284
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.04139365574622985
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.022704108164326574
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.015822499566649332
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.012189287571502862
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.1547198078399326
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.652070178045217
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.7639576059232845
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.8390052744966942
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.877764158185375
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.9016677809969541
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.40717628705148207
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.5052212563002627
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.5356805472279078
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.5521009256440798
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.5595924746165437
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.5639157869620031
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.40717628705148207
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.49319826751048873
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.49612329710657893
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.4969826860284758
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.49724671253026886
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.49734552981578295
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.40717628705148207
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.419614969499609
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.427088485280225
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.4292014145714
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.4298202694277485
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.4300980044671579
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.43055010151569684
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix de
          type: mix_de
        metrics:
          - type: cosine_accuracy@1
            value: 0.29017160686427457
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.6484659386375455
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.7540301612064483
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.8419136765470618
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.8788351534061363
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9089963598543942
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.29017160686427457
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.07251690067602704
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.0355486219448778
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.02041601664066563
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.014505113537874847
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.01137545501820073
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.10890968972092217
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.5299011960478419
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.647191887675507
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.7442624371641533
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.7928583810019068
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.8289478245796498
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.29017160686427457
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.38598145754556046
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.41773491829410075
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.43906545567486005
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.4485955578737219
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.45520732213321263
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.29017160686427457
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.37232551415227233
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.375685507642469
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.3769348294784883
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.377239930826995
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.3774183771765249
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.29017160686427457
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.30311022602590254
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.31036427264538485
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.31304585670015317
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.3138396622777036
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.31426372512191
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.3150399864057635
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix zh
          type: mix_zh
        metrics:
          - type: cosine_accuracy@1
            value: 0.09394572025052192
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.35281837160751567
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.48329853862212946
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.5918580375782881
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.6649269311064718
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.7004175365344467
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.09394572025052192
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.030897703549060546
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.018204592901878917
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.011362212943632568
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.008639526791927627
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.007019832985386221
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.03185455810716771
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.20592877025549258
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.30069837956059253
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.3754792557245584
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.4282591046160983
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.46372361401067036
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.09394572025052192
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.13433471892252347
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.16091824243484512
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.1780017996510726
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.1886875211403746
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.19541417908856412
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.09394572025052192
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.14710513443845905
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.15122849766144658
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.15275090014884107
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.1533445728241347
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.1535456563541225
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.09394572025052192
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.083759101073897
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.08908800548950695
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.09092612397080438
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.09168814149038751
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.09208168156532727
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.09301554391402207
            name: Cosine Map@500

SentenceTransformer based on BAAI/bge-small-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5 on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: BAAI/bge-small-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Datasets:
  • full_en
  • full_de
  • full_es
  • full_zh
  • mix

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

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 SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'Volksvertreter',
    'Parlamentarier',
    'Oberbürgermeister',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Datasets: full_en, full_es, full_de, full_zh, mix_es, mix_de and mix_zh
• Evaluated with InformationRetrievalEvaluator

Metric	full_en	full_es	full_de	full_zh	mix_es	mix_de	mix_zh
cosine_accuracy@1	0.6571	0.1243	0.2956	0.301	0.4072	0.2902	0.0939
cosine_accuracy@20	0.9905	1.0	0.9212	0.7087	0.7582	0.6485	0.3528
cosine_accuracy@50	0.9905	1.0	0.9606	0.8252	0.8456	0.754	0.4833
cosine_accuracy@100	0.9905	1.0	0.9754	0.8544	0.9048	0.8419	0.5919
cosine_accuracy@150	0.9905	1.0	0.9852	0.9126	0.9371	0.8788	0.6649
cosine_accuracy@200	0.9905	1.0	0.9852	0.9417	0.9548	0.909	0.7004
cosine_precision@1	0.6571	0.1243	0.2956	0.301	0.4072	0.2902	0.0939
cosine_precision@20	0.5076	0.4924	0.4227	0.1684	0.0882	0.0725	0.0309
cosine_precision@50	0.309	0.3169	0.2775	0.0944	0.0414	0.0355	0.0182
cosine_precision@100	0.1872	0.1984	0.1787	0.0584	0.0227	0.0204	0.0114
cosine_precision@150	0.1322	0.147	0.135	0.046	0.0158	0.0145	0.0086
cosine_precision@200	0.1027	0.1176	0.1096	0.0382	0.0122	0.0114	0.007
cosine_recall@1	0.068	0.0031	0.0111	0.0244	0.1547	0.1089	0.0319
cosine_recall@20	0.5459	0.3236	0.2579	0.1751	0.6521	0.5299	0.2059
cosine_recall@50	0.7285	0.4623	0.3785	0.2395	0.764	0.6472	0.3007
cosine_recall@100	0.8382	0.5424	0.4647	0.286	0.839	0.7443	0.3755
cosine_recall@150	0.8762	0.5823	0.5141	0.3291	0.8778	0.7929	0.4283
cosine_recall@200	0.906	0.6126	0.5479	0.363	0.9017	0.8289	0.4637
cosine_ndcg@1	0.6571	0.1243	0.2956	0.301	0.4072	0.2902	0.0939
cosine_ndcg@20	0.6895	0.5407	0.4572	0.2385	0.5052	0.386	0.1343
cosine_ndcg@50	0.7061	0.5008	0.4186	0.2342	0.5357	0.4177	0.1609
cosine_ndcg@100	0.762	0.5143	0.4341	0.2559	0.5521	0.4391	0.178
cosine_ndcg@150	0.7788	0.535	0.4594	0.2734	0.5596	0.4486	0.1887
cosine_ndcg@200	0.79	0.5498	0.4763	0.2857	0.5639	0.4552	0.1954
cosine_mrr@1	0.6571	0.1243	0.2956	0.301	0.4072	0.2902	0.0939
cosine_mrr@20	0.8098	0.5517	0.4885	0.4211	0.4932	0.3723	0.1471
cosine_mrr@50	0.8098	0.5517	0.4898	0.425	0.4961	0.3757	0.1512
cosine_mrr@100	0.8098	0.5517	0.49	0.4254	0.497	0.3769	0.1528
cosine_mrr@150	0.8098	0.5517	0.4901	0.4259	0.4972	0.3772	0.1533
cosine_mrr@200	0.8098	0.5517	0.4901	0.426	0.4973	0.3774	0.1535
cosine_map@1	0.6571	0.1243	0.2956	0.301	0.4072	0.2902	0.0939
cosine_map@20	0.5465	0.4062	0.3211	0.1416	0.4196	0.3031	0.0838
cosine_map@50	0.5352	0.3426	0.2619	0.1233	0.4271	0.3104	0.0891
cosine_map@100	0.5685	0.3398	0.2559	0.1288	0.4292	0.313	0.0909
cosine_map@150	0.5757	0.3482	0.265	0.1315	0.4298	0.3138	0.0917
cosine_map@200	0.5792	0.3535	0.2701	0.1329	0.4301	0.3143	0.0921
cosine_map@500	0.5835	0.3635	0.2811	0.1368	0.4306	0.315	0.093

Training Details

Training Datasets

full_en

full_en

• Dataset: full_en
• Size: 28,880 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 5.0 tokens max: 10 tokens	min: 3 tokens mean: 5.01 tokens max: 13 tokens

• Samples:

  anchor	positive
  air commodore	flight lieutenant
  command and control officer	flight officer
  air commodore	command and control officer

• Loss: GISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (2): Normalize()
  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
  

full_de

full_de

• Dataset: full_de
• Size: 23,023 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 11.05 tokens max: 45 tokens	min: 3 tokens mean: 11.43 tokens max: 45 tokens

• Samples:

  anchor	positive
  Staffelkommandantin	Kommodore
  Luftwaffenoffizierin	Luftwaffenoffizier/Luftwaffenoffizierin
  Staffelkommandantin	Luftwaffenoffizierin

• Loss: GISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (2): Normalize()
  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
  

full_es

full_es

• Dataset: full_es
• Size: 20,724 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 12.95 tokens max: 50 tokens	min: 3 tokens mean: 12.57 tokens max: 50 tokens

• Samples:

  anchor	positive
  jefe de escuadrón	instructor
  comandante de aeronave	instructor de simulador
  instructor	oficial del Ejército del Aire

• Loss: GISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (2): Normalize()
  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
  

full_zh

full_zh

• Dataset: full_zh
• Size: 30,401 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 4 tokens mean: 8.36 tokens max: 20 tokens	min: 4 tokens mean: 8.95 tokens max: 27 tokens

• Samples:

  anchor	positive
  技术总监	技术和运营总监
  技术总监	技术主管
  技术总监	技术艺术总监

• Loss: GISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (2): Normalize()
  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
  

mix

mix

• Dataset: mix
• Size: 21,760 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 2 tokens mean: 5.65 tokens max: 14 tokens	min: 2 tokens mean: 10.08 tokens max: 30 tokens

• Samples:

  anchor	positive
  technical manager	Technischer Direktor für Bühne, Film und Fernsehen
  head of technical	directora técnica
  head of technical department	技术艺术总监

• Loss: GISTEmbedLoss with these parameters:

  {'guide': SentenceTransformer(
    (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (2): Normalize()
  ), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• gradient_accumulation_steps: 2
• num_train_epochs: 5
• warmup_ratio: 0.05
• log_on_each_node: False
• fp16: True
• dataloader_num_workers: 4
• ddp_find_unused_parameters: 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: 128
• per_device_eval_batch_size: 128
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-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: 5
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.05
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: False
• 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: False
• fp16: True
• 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: True
• dataloader_num_workers: 4
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• 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: True
• 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

Training Logs

Epoch	Step	Training Loss	full_en_cosine_ndcg@200	full_es_cosine_ndcg@200	full_de_cosine_ndcg@200	full_zh_cosine_ndcg@200	mix_es_cosine_ndcg@200	mix_de_cosine_ndcg@200	mix_zh_cosine_ndcg@200
-1	-1	-	0.7322	0.4690	0.3853	0.2723	0.3209	0.2244	0.0919
0.0021	1	23.8878	-	-	-	-	-	-	-
0.2058	100	7.2098	-	-	-	-	-	-	-
0.4115	200	4.2635	0.7800	0.5132	0.4268	0.2798	0.4372	0.2996	0.1447
0.6173	300	4.1931	-	-	-	-	-	-	-
0.8230	400	3.73	0.7863	0.5274	0.4451	0.2805	0.4762	0.3455	0.1648
1.0309	500	3.3569	-	-	-	-	-	-	-
1.2366	600	3.6464	0.7868	0.5372	0.4540	0.2813	0.5063	0.3794	0.1755
1.4424	700	3.0772	-	-	-	-	-	-	-
1.6481	800	3.114	0.7906	0.5391	0.4576	0.2832	0.5221	0.4047	0.1779
1.8539	900	2.9246	-	-	-	-	-	-	-
2.0617	1000	2.7479	0.7873	0.5423	0.4631	0.2871	0.5323	0.4143	0.1843
2.2675	1100	3.049	-	-	-	-	-	-	-
2.4733	1200	2.6137	0.7878	0.5418	0.4685	0.2870	0.5470	0.4339	0.1932
2.6790	1300	2.8607	-	-	-	-	-	-	-
2.8848	1400	2.7071	0.7889	0.5465	0.4714	0.2891	0.5504	0.4362	0.1944
3.0926	1500	2.7012	-	-	-	-	-	-	-
3.2984	1600	2.7423	0.7882	0.5471	0.4748	0.2868	0.5542	0.4454	0.1976
3.5041	1700	2.5316	-	-	-	-	-	-	-
3.7099	1800	2.6344	0.7900	0.5498	0.4763	0.2857	0.5639	0.4552	0.1954

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.5.0
• 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",
}

GISTEmbedLoss

@misc{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    year={2024},
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}