checkpoint-2200/README.md

---
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: 0.5047619047619047
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.30857142857142855
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.18666666666666668
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.13269841269841268
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.1029047619047619
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.0680237860830842
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.539060339827615
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.7269844521994231
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.8337131628681403
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.879935375805825
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.9050529457831012
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.6571428571428571
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.686462471196106
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.7052824081502371
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.7601614355798527
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.7798476891938094
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.7898871141566125
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.6571428571428571
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.8095238095238095
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.8095238095238095
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.8095238095238095
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.8095238095238095
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.8095238095238095
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.6571428571428571
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.5451065538458748
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.5347802076206865
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.567702602098158
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.5756725358487015
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.5789669196636947
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.5832808543489026
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: full es
      type: full_es
    metrics:
    - type: cosine_accuracy@1
      value: 0.11351351351351352
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 1.0
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 1.0
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 1.0
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 1.0
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 1.0
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.11351351351351352
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.4913513513513514
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.316972972972973
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.19843243243243244
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.146990990990991
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.11778378378378378
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.002992884071419607
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.32341666838263944
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.4630260221149236
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.5419804526017848
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.5826718468403144
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.6149262657286421
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.11351351351351352
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.5389058089458943
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.5002442028172164
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.5138591255215345
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.5346372349516221
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.5502474315848075
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.11351351351351352
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.5444744744744745
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.5444744744744745
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.5444744744744745
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.5444744744744745
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.5444744744744745
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.11351351351351352
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.40352984921129137
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.3418539578142162
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.339373689987275
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.3478760829213016
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.3533435915341769
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.363222785830563
      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: 0.9655172413793104
      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: 0.424384236453202
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.28167487684729065
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.17995073891625615
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.13589490968801315
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.1108128078817734
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.01108543831680986
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.2600945586038909
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.3844030994839744
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.4672649807153451
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.5171228717670064
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.5533299912627624
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.2955665024630542
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.4593107411252075
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.42313178566078624
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.4367043857530601
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.4621847371016286
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.48019099347834654
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.2955665024630542
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.4892678749821603
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.49065090899064223
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.49080251743966435
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.4908799208299932
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.4908799208299932
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.2955665024630542
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.3228620941051522
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.2644260812747752
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.2576011230547815
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.2666548881846307
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.27224102651692533
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.28312561300678324
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: full zh
      type: full_zh
    metrics:
    - type: cosine_accuracy@1
      value: 0.3300970873786408
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.7184466019417476
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.8155339805825242
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.8932038834951457
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9223300970873787
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9320388349514563
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.3300970873786408
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.16796116504854372
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.09262135922330093
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.05815533980582525
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.04563106796116505
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.03771844660194174
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.02573649124630195
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.17402459309945448
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.23816219248808224
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.28291725637657983
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.32619122038725784
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.3543394793587958
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.3300970873786408
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.23956118764265208
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.2341910409667355
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.2559822552765659
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.27344655996496936
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.28432223965649855
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.3300970873786408
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.43064643766798927
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.43374387043765733
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.4348781442268605
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.4351279925655956
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.4351822313246128
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.3300970873786408
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.14301006319225865
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.12425793473074002
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.12962575663735706
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.13242860022521366
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.13374255185989983
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.13779434547799502
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix es
      type: mix_es
    metrics:
    - type: cosine_accuracy@1
      value: 0.40977639105564223
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.7618304732189287
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.8512740509620385
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.9105564222568903
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9381175247009881
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9542381695267811
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.40977639105564223
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.0890015600624025
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.04168486739469579
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.022854914196567863
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.01585370081469925
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.012220488819552783
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.15567317930812472
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.6574783943738703
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.7691404799049105
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.8454015303469281
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.8795148948815096
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.9035051878265606
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.40977639105564223
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.5094055696124096
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.5398029704628499
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.5563939454831869
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.5630335952477792
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.5674217099859529
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.40977639105564223
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.4963374711503733
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.49930745416180927
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.5001571935146001
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.5003842041203103
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.5004783417497985
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.40977639105564223
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.4236549905504724
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.4311498037279026
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.43327838927965695
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.4338451382952763
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.4341307997461715
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.4345995592976099
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix de
      type: mix_de
    metrics:
    - type: cosine_accuracy@1
      value: 0.2912116484659386
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.6526261050442018
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.7550702028081123
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.8460738429537181
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.8876755070202809
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9173166926677067
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.2912116484659386
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.07308892355694228
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.03583983359334374
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.02058242329693188
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.014609117698041255
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.011515860634425378
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.10977639105564223
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.5342520367481365
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.6529207834980065
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.7505633558675681
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.7989166233315999
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.8393482405962905
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.2912116484659386
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.39027078330836906
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.4224011615840446
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.4438393956774872
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.45327900259303716
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.4606831999024183
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.2912116484659386
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.37544207546115405
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.37870409367323543
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.37999194359776256
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.3803335431113417
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.3805079454038972
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.2912116484659386
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.3075927383942124
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.31502827814698436
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.31767149302992986
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.31842095656425334
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.3189017921904424
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.31963709557315734
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix zh
      type: mix_zh
    metrics:
    - type: cosine_accuracy@1
      value: 0.09498956158663883
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.35281837160751567
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.48851774530271397
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.5960334029227558
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.657098121085595
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.7025052192066806
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.09498956158663883
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.03102818371607516
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.018528183716075158
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.011550104384133612
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.008601252609603338
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.007074634655532359
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.03218510786360473
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.20682473406899293
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.30616239188786165
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.38175970109686186
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.4266063558339132
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.4677598005103224
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.09498956158663883
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.13726194438538974
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.16515347653846224
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.18245718935168395
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.1915123607890909
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.1993072789458329
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.09498956158663883
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.15082760305134044
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.1552139914541245
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.1567682757261486
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.1572599746321091
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.15752063728764779
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.09498956158663883
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.08696228866764828
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.0925585898977933
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.09443690504503688
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.09508196706389692
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.09552658777692054
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.09647934265199021
      name: Cosine Map@500
---

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

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en-v1.5](https://huggingface.co/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](https://huggingface.co/BAAI/bge-small-en-v1.5) <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Datasets:**
    - full_en
    - full_de
    - full_es
    - full_zh
    - mix
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### Model Sources

- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

### 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:

```bash
pip install -U sentence-transformers
```

Then you can load this model and run inference.
```python
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]
```

<!--
### Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details>
-->

<!--
### Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details>
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

## Evaluation

### Metrics

#### Information Retrieval

* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

| Metric               | full_en    | full_es    | full_de    | full_zh    | mix_es     | mix_de     | mix_zh     |
|:---------------------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
| cosine_accuracy@1    | 0.6571     | 0.1135     | 0.2956     | 0.3301     | 0.4098     | 0.2912     | 0.095      |
| cosine_accuracy@20   | 0.9905     | 1.0        | 0.9212     | 0.7184     | 0.7618     | 0.6526     | 0.3528     |
| cosine_accuracy@50   | 0.9905     | 1.0        | 0.9655     | 0.8155     | 0.8513     | 0.7551     | 0.4885     |
| cosine_accuracy@100  | 0.9905     | 1.0        | 0.9754     | 0.8932     | 0.9106     | 0.8461     | 0.596      |
| cosine_accuracy@150  | 0.9905     | 1.0        | 0.9852     | 0.9223     | 0.9381     | 0.8877     | 0.6571     |
| cosine_accuracy@200  | 0.9905     | 1.0        | 0.9852     | 0.932      | 0.9542     | 0.9173     | 0.7025     |
| cosine_precision@1   | 0.6571     | 0.1135     | 0.2956     | 0.3301     | 0.4098     | 0.2912     | 0.095      |
| cosine_precision@20  | 0.5048     | 0.4914     | 0.4244     | 0.168      | 0.089      | 0.0731     | 0.031      |
| cosine_precision@50  | 0.3086     | 0.317      | 0.2817     | 0.0926     | 0.0417     | 0.0358     | 0.0185     |
| cosine_precision@100 | 0.1867     | 0.1984     | 0.18       | 0.0582     | 0.0229     | 0.0206     | 0.0116     |
| cosine_precision@150 | 0.1327     | 0.147      | 0.1359     | 0.0456     | 0.0159     | 0.0146     | 0.0086     |
| cosine_precision@200 | 0.1029     | 0.1178     | 0.1108     | 0.0377     | 0.0122     | 0.0115     | 0.0071     |
| cosine_recall@1      | 0.068      | 0.003      | 0.0111     | 0.0257     | 0.1557     | 0.1098     | 0.0322     |
| cosine_recall@20     | 0.5391     | 0.3234     | 0.2601     | 0.174      | 0.6575     | 0.5343     | 0.2068     |
| cosine_recall@50     | 0.727      | 0.463      | 0.3844     | 0.2382     | 0.7691     | 0.6529     | 0.3062     |
| cosine_recall@100    | 0.8337     | 0.542      | 0.4673     | 0.2829     | 0.8454     | 0.7506     | 0.3818     |
| cosine_recall@150    | 0.8799     | 0.5827     | 0.5171     | 0.3262     | 0.8795     | 0.7989     | 0.4266     |
| cosine_recall@200    | 0.9051     | 0.6149     | 0.5533     | 0.3543     | 0.9035     | 0.8393     | 0.4678     |
| cosine_ndcg@1        | 0.6571     | 0.1135     | 0.2956     | 0.3301     | 0.4098     | 0.2912     | 0.095      |
| cosine_ndcg@20       | 0.6865     | 0.5389     | 0.4593     | 0.2396     | 0.5094     | 0.3903     | 0.1373     |
| cosine_ndcg@50       | 0.7053     | 0.5002     | 0.4231     | 0.2342     | 0.5398     | 0.4224     | 0.1652     |
| cosine_ndcg@100      | 0.7602     | 0.5139     | 0.4367     | 0.256      | 0.5564     | 0.4438     | 0.1825     |
| cosine_ndcg@150      | 0.7798     | 0.5346     | 0.4622     | 0.2734     | 0.563      | 0.4533     | 0.1915     |
| **cosine_ndcg@200**  | **0.7899** | **0.5502** | **0.4802** | **0.2843** | **0.5674** | **0.4607** | **0.1993** |
| cosine_mrr@1         | 0.6571     | 0.1135     | 0.2956     | 0.3301     | 0.4098     | 0.2912     | 0.095      |
| cosine_mrr@20        | 0.8095     | 0.5445     | 0.4893     | 0.4306     | 0.4963     | 0.3754     | 0.1508     |
| cosine_mrr@50        | 0.8095     | 0.5445     | 0.4907     | 0.4337     | 0.4993     | 0.3787     | 0.1552     |
| cosine_mrr@100       | 0.8095     | 0.5445     | 0.4908     | 0.4349     | 0.5002     | 0.38       | 0.1568     |
| cosine_mrr@150       | 0.8095     | 0.5445     | 0.4909     | 0.4351     | 0.5004     | 0.3803     | 0.1573     |
| cosine_mrr@200       | 0.8095     | 0.5445     | 0.4909     | 0.4352     | 0.5005     | 0.3805     | 0.1575     |
| cosine_map@1         | 0.6571     | 0.1135     | 0.2956     | 0.3301     | 0.4098     | 0.2912     | 0.095      |
| cosine_map@20        | 0.5451     | 0.4035     | 0.3229     | 0.143      | 0.4237     | 0.3076     | 0.087      |
| cosine_map@50        | 0.5348     | 0.3419     | 0.2644     | 0.1243     | 0.4311     | 0.315      | 0.0926     |
| cosine_map@100       | 0.5677     | 0.3394     | 0.2576     | 0.1296     | 0.4333     | 0.3177     | 0.0944     |
| cosine_map@150       | 0.5757     | 0.3479     | 0.2667     | 0.1324     | 0.4338     | 0.3184     | 0.0951     |
| cosine_map@200       | 0.579      | 0.3533     | 0.2722     | 0.1337     | 0.4341     | 0.3189     | 0.0955     |
| cosine_map@500       | 0.5833     | 0.3632     | 0.2831     | 0.1378     | 0.4346     | 0.3196     | 0.0965     |

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Datasets
<details><summary>full_en</summary>

#### full_en

* Dataset: full_en
* Size: 28,880 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                          | positive                                                                         |
  |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
  | type    | string                                                                          | string                                                                           |
  | details | <ul><li>min: 3 tokens</li><li>mean: 5.0 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.01 tokens</li><li>max: 13 tokens</li></ul> |
* Samples:
  | anchor                                   | positive                                 |
  |:-----------------------------------------|:-----------------------------------------|
  | <code>air commodore</code>               | <code>flight lieutenant</code>           |
  | <code>command and control officer</code> | <code>flight officer</code>              |
  | <code>air commodore</code>               | <code>command and control officer</code> |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
  ```json
  {'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}
  ```
</details>
<details><summary>full_de</summary>

#### full_de

* Dataset: full_de
* Size: 23,023 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                            | positive                                                                          |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                            | string                                                                            |
  | details | <ul><li>min: 3 tokens</li><li>mean: 11.05 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 11.43 tokens</li><li>max: 45 tokens</li></ul> |
* Samples:
  | anchor                            | positive                                             |
  |:----------------------------------|:-----------------------------------------------------|
  | <code>Staffelkommandantin</code>  | <code>Kommodore</code>                               |
  | <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
  | <code>Staffelkommandantin</code>  | <code>Luftwaffenoffizierin</code>                    |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
  ```json
  {'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}
  ```
</details>
<details><summary>full_es</summary>

#### full_es

* Dataset: full_es
* Size: 20,724 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                            | positive                                                                          |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                            | string                                                                            |
  | details | <ul><li>min: 3 tokens</li><li>mean: 12.95 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 12.57 tokens</li><li>max: 50 tokens</li></ul> |
* Samples:
  | anchor                              | positive                                   |
  |:------------------------------------|:-------------------------------------------|
  | <code>jefe de escuadrón</code>      | <code>instructor</code>                    |
  | <code>comandante de aeronave</code> | <code>instructor de simulador</code>       |
  | <code>instructor</code>             | <code>oficial del Ejército del Aire</code> |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
  ```json
  {'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}
  ```
</details>
<details><summary>full_zh</summary>

#### full_zh

* Dataset: full_zh
* Size: 30,401 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                           | positive                                                                         |
  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
  | type    | string                                                                           | string                                                                           |
  | details | <ul><li>min: 4 tokens</li><li>mean: 8.36 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.95 tokens</li><li>max: 27 tokens</li></ul> |
* Samples:
  | anchor            | positive             |
  |:------------------|:---------------------|
  | <code>技术总监</code> | <code>技术和运营总监</code> |
  | <code>技术总监</code> | <code>技术主管</code>    |
  | <code>技术总监</code> | <code>技术艺术总监</code>  |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
  ```json
  {'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}
  ```
</details>
<details><summary>mix</summary>

#### mix

* Dataset: mix
* Size: 21,760 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                           | positive                                                                          |
  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                           | string                                                                            |
  | details | <ul><li>min: 2 tokens</li><li>mean: 5.65 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 10.08 tokens</li><li>max: 30 tokens</li></ul> |
* Samples:
  | anchor                                    | positive                                                        |
  |:------------------------------------------|:----------------------------------------------------------------|
  | <code>technical manager</code>            | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
  | <code>head of technical</code>            | <code>directora técnica</code>                                  |
  | <code>head of technical department</code> | <code>技术艺术总监</code>                                             |
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
  ```json
  {'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}
  ```
</details>

### 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
<details><summary>Click to expand</summary>

- `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

</details>

### 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                 |
| 3.9156 | 1900 | 2.4983        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 4.1235 | 2000 | 2.5423        | 0.7894                  | 0.5499                  | 0.4786                  | 0.2870                  | 0.5644                 | 0.4576                 | 0.1974                 |
| 4.3292 | 2100 | 2.5674        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 4.5350 | 2200 | 2.6237        | 0.7899                  | 0.5502                  | 0.4802                  | 0.2843                  | 0.5674                 | 0.4607                 | 0.1993                 |


### 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
```bibtex
@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
```bibtex
@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}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->