checkpoint-4000/README.md

---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:124788
- loss:GISTEmbedLoss
base_model: BAAI/bge-m3
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-m3
  results:
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: full en
      type: full_en
    metrics:
    - type: cosine_accuracy@1
      value: 0.6476190476190476
      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: 0.6476190476190476
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.499047619047619
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.30266666666666664
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.18447619047619046
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.13155555555555554
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.10171428571428573
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.06690172806447445
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.5288155255988508
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.7128731386766649
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.821589853989195
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.8669290529739844
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.8881772271562451
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.6476190476190476
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.6737021289484512
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.6897381539459008
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.7455379155828873
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.7657730626526685
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.7746920852324353
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.6476190476190476
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.7969444444444443
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.7969444444444443
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.7969444444444443
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.7969444444444443
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.7969444444444443
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.6476190476190476
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.5299368408688423
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.5170402457535271
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.549577105065989
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.5580348324082148
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.5609705433942662
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.5664835460503455
      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: 1.0
      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: 0.12432432432432433
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.5718918918918918
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.38832432432432434
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.25135135135135134
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.1886486486486487
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.15083783783783786
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.0036542148230633313
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.3813088657975513
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.5589819018381946
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.6712879484837694
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.7296378671854172
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.7646529145750729
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.12432432432432433
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.6162786673767947
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.5875500387824142
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.6146487956773306
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.6449661586574366
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.6628313427507618
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.12432432432432433
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.5585585585585586
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.5585585585585586
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.5585585585585586
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.5585585585585586
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.5585585585585586
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.12432432432432433
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.4830935685993706
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.4268637780839156
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.43032040469750343
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.4449589410699155
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.4523102942291434
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.4643631946508736
      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: 0.9753694581280788
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.9852216748768473
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.9852216748768473
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9901477832512315
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9901477832512315
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.2955665024630542
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.5399014778325123
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.3829556650246305
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.25098522167487686
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.18742200328407224
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.14911330049261085
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.01108543831680986
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.33926725064737134
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.5319613376214742
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.6497082600959269
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.7094703332321319
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.7445597670438818
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.2955665024630542
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.5621043185251402
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.5505636839954736
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.5784375922614946
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.6091764880384499
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.6263384735475871
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.2955665024630542
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.5127296895769795
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.5130763416477695
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.5130763416477695
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.5131188080992728
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.5131188080992728
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.2955665024630542
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.42085554479107096
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.3779379416896035
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.38163165810143573
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.3961646378244818
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.40295816570523324
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.4167002568710484
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: full zh
      type: full_zh
    metrics:
    - type: cosine_accuracy@1
      value: 0.6407766990291263
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.9902912621359223
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.9902912621359223
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.9902912621359223
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9902912621359223
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9902912621359223
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.6407766990291263
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.46504854368932047
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.27611650485436895
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.17097087378640777
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.12291262135922332
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.0969417475728155
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.05744396078263393
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.4978573021507442
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.6611813069264482
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.7796553453979224
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.8271677009796732
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.8637730394316714
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.6407766990291263
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.6374339653798218
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.6458466090741598
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.7026844413104963
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.7238302410564206
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.7383757321568225
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.6407766990291263
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.7983818770226538
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.7983818770226538
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.7983818770226538
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.7983818770226538
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.7983818770226538
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.6407766990291263
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.4902515378001179
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.46828607843970593
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.49742002930709256
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.5055517135202557
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.5100267276205871
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.5152273086702759
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix es
      type: mix_es
    metrics:
    - type: cosine_accuracy@1
      value: 0.7358294331773271
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.9625585023400937
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.9802392095683827
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.9927197087883516
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9947997919916797
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9958398335933437
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.7358294331773271
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.12438897555902236
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.05158606344253771
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.026224648985959446
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.017628705148205928
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.013268330733229333
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.28403164698016486
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.9190414283237995
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.952244756456925
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.9685820766163981
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.9762870514820593
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.9801872074882996
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.7358294331773271
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.8089516774866639
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.8181299102768375
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.8217009899252086
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.8232345422421572
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.8239096085290897
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.7358294331773271
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.8035232306901704
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.8041564269676074
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.8043491602665708
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.8043649132860833
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.8043707455995762
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.7358294331773271
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.7407296211762635
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.7433011890905112
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.7437599072934008
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.7439220951644092
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.7439677461223776
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.7440630263326289
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix de
      type: mix_de
    metrics:
    - type: cosine_accuracy@1
      value: 0.6947477899115965
      name: Cosine Accuracy@1
    - type: cosine_accuracy@20
      value: 0.967758710348414
      name: Cosine Accuracy@20
    - type: cosine_accuracy@50
      value: 0.984399375975039
      name: Cosine Accuracy@50
    - type: cosine_accuracy@100
      value: 0.9901196047841914
      name: Cosine Accuracy@100
    - type: cosine_accuracy@150
      value: 0.9932397295891836
      name: Cosine Accuracy@150
    - type: cosine_accuracy@200
      value: 0.9932397295891836
      name: Cosine Accuracy@200
    - type: cosine_precision@1
      value: 0.6947477899115965
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.12769110764430577
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.05316692667706709
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.026978679147165893
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.018082856647599233
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.013595943837753513
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.26064309239036226
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 0.9266163979892529
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 0.9632518634078697
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 0.9771190847633905
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 0.982232622638239
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 0.984659386375455
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.6947477899115965
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.7916550876560119
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.8018356667177752
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.8049830038156018
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.8060041518104935
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.8064526867706615
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.6947477899115965
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.775106319970792
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.7756762344136855
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.7757636235577245
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.7757917238264626
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.7757917238264626
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.6947477899115965
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.7123386461179687
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.7151736057555711
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.7156740227134941
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.7157705885677804
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.7158097678043102
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.7158747359338941
      name: Cosine Map@500
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: mix zh
      type: mix_zh
    metrics:
    - type: cosine_accuracy@1
      value: 0.1814872594903796
      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: 0.1814872594903796
      name: Cosine Precision@1
    - type: cosine_precision@20
      value: 0.15439417576703063
      name: Cosine Precision@20
    - type: cosine_precision@50
      value: 0.0617576703068123
      name: Cosine Precision@50
    - type: cosine_precision@100
      value: 0.03087883515340615
      name: Cosine Precision@100
    - type: cosine_precision@150
      value: 0.020585890102270757
      name: Cosine Precision@150
    - type: cosine_precision@200
      value: 0.015439417576703075
      name: Cosine Precision@200
    - type: cosine_recall@1
      value: 0.058722729861575416
      name: Cosine Recall@1
    - type: cosine_recall@20
      value: 1.0
      name: Cosine Recall@20
    - type: cosine_recall@50
      value: 1.0
      name: Cosine Recall@50
    - type: cosine_recall@100
      value: 1.0
      name: Cosine Recall@100
    - type: cosine_recall@150
      value: 1.0
      name: Cosine Recall@150
    - type: cosine_recall@200
      value: 1.0
      name: Cosine Recall@200
    - type: cosine_ndcg@1
      value: 0.1814872594903796
      name: Cosine Ndcg@1
    - type: cosine_ndcg@20
      value: 0.5447038314336347
      name: Cosine Ndcg@20
    - type: cosine_ndcg@50
      value: 0.5447038314336347
      name: Cosine Ndcg@50
    - type: cosine_ndcg@100
      value: 0.5447038314336347
      name: Cosine Ndcg@100
    - type: cosine_ndcg@150
      value: 0.5447038314336347
      name: Cosine Ndcg@150
    - type: cosine_ndcg@200
      value: 0.5447038314336347
      name: Cosine Ndcg@200
    - type: cosine_mrr@1
      value: 0.1814872594903796
      name: Cosine Mrr@1
    - type: cosine_mrr@20
      value: 0.40366659543726713
      name: Cosine Mrr@20
    - type: cosine_mrr@50
      value: 0.40366659543726713
      name: Cosine Mrr@50
    - type: cosine_mrr@100
      value: 0.40366659543726713
      name: Cosine Mrr@100
    - type: cosine_mrr@150
      value: 0.40366659543726713
      name: Cosine Mrr@150
    - type: cosine_mrr@200
      value: 0.40366659543726713
      name: Cosine Mrr@200
    - type: cosine_map@1
      value: 0.1814872594903796
      name: Cosine Map@1
    - type: cosine_map@20
      value: 0.32665499722442
      name: Cosine Map@20
    - type: cosine_map@50
      value: 0.32665499722442
      name: Cosine Map@50
    - type: cosine_map@100
      value: 0.32665499722442
      name: Cosine Map@100
    - type: cosine_map@150
      value: 0.32665499722442
      name: Cosine Map@150
    - type: cosine_map@200
      value: 0.32665499722442
      name: Cosine Map@200
    - type: cosine_map@500
      value: 0.32665499722442
      name: Cosine Map@500
---

# SentenceTransformer based on BAAI/bge-m3

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 1024-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-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 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': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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, 1024]

# 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    | 0.6476     | 0.1243     | 0.2956     | 0.6408     | 0.7358     | 0.6947     | 0.1815     |
| cosine_accuracy@20   | 0.9905     | 1.0        | 0.9754     | 0.9903     | 0.9626     | 0.9678     | 1.0        |
| cosine_accuracy@50   | 0.9905     | 1.0        | 0.9852     | 0.9903     | 0.9802     | 0.9844     | 1.0        |
| cosine_accuracy@100  | 0.9905     | 1.0        | 0.9852     | 0.9903     | 0.9927     | 0.9901     | 1.0        |
| cosine_accuracy@150  | 0.9905     | 1.0        | 0.9901     | 0.9903     | 0.9948     | 0.9932     | 1.0        |
| cosine_accuracy@200  | 0.9905     | 1.0        | 0.9901     | 0.9903     | 0.9958     | 0.9932     | 1.0        |
| cosine_precision@1   | 0.6476     | 0.1243     | 0.2956     | 0.6408     | 0.7358     | 0.6947     | 0.1815     |
| cosine_precision@20  | 0.499      | 0.5719     | 0.5399     | 0.465      | 0.1244     | 0.1277     | 0.1544     |
| cosine_precision@50  | 0.3027     | 0.3883     | 0.383      | 0.2761     | 0.0516     | 0.0532     | 0.0618     |
| cosine_precision@100 | 0.1845     | 0.2514     | 0.251      | 0.171      | 0.0262     | 0.027      | 0.0309     |
| cosine_precision@150 | 0.1316     | 0.1886     | 0.1874     | 0.1229     | 0.0176     | 0.0181     | 0.0206     |
| cosine_precision@200 | 0.1017     | 0.1508     | 0.1491     | 0.0969     | 0.0133     | 0.0136     | 0.0154     |
| cosine_recall@1      | 0.0669     | 0.0037     | 0.0111     | 0.0574     | 0.284      | 0.2606     | 0.0587     |
| cosine_recall@20     | 0.5288     | 0.3813     | 0.3393     | 0.4979     | 0.919      | 0.9266     | 1.0        |
| cosine_recall@50     | 0.7129     | 0.559      | 0.532      | 0.6612     | 0.9522     | 0.9633     | 1.0        |
| cosine_recall@100    | 0.8216     | 0.6713     | 0.6497     | 0.7797     | 0.9686     | 0.9771     | 1.0        |
| cosine_recall@150    | 0.8669     | 0.7296     | 0.7095     | 0.8272     | 0.9763     | 0.9822     | 1.0        |
| cosine_recall@200    | 0.8882     | 0.7647     | 0.7446     | 0.8638     | 0.9802     | 0.9847     | 1.0        |
| cosine_ndcg@1        | 0.6476     | 0.1243     | 0.2956     | 0.6408     | 0.7358     | 0.6947     | 0.1815     |
| cosine_ndcg@20       | 0.6737     | 0.6163     | 0.5621     | 0.6374     | 0.809      | 0.7917     | 0.5447     |
| cosine_ndcg@50       | 0.6897     | 0.5876     | 0.5506     | 0.6458     | 0.8181     | 0.8018     | 0.5447     |
| cosine_ndcg@100      | 0.7455     | 0.6146     | 0.5784     | 0.7027     | 0.8217     | 0.805      | 0.5447     |
| cosine_ndcg@150      | 0.7658     | 0.645      | 0.6092     | 0.7238     | 0.8232     | 0.806      | 0.5447     |
| **cosine_ndcg@200**  | **0.7747** | **0.6628** | **0.6263** | **0.7384** | **0.8239** | **0.8065** | **0.5447** |
| cosine_mrr@1         | 0.6476     | 0.1243     | 0.2956     | 0.6408     | 0.7358     | 0.6947     | 0.1815     |
| cosine_mrr@20        | 0.7969     | 0.5586     | 0.5127     | 0.7984     | 0.8035     | 0.7751     | 0.4037     |
| cosine_mrr@50        | 0.7969     | 0.5586     | 0.5131     | 0.7984     | 0.8042     | 0.7757     | 0.4037     |
| cosine_mrr@100       | 0.7969     | 0.5586     | 0.5131     | 0.7984     | 0.8043     | 0.7758     | 0.4037     |
| cosine_mrr@150       | 0.7969     | 0.5586     | 0.5131     | 0.7984     | 0.8044     | 0.7758     | 0.4037     |
| cosine_mrr@200       | 0.7969     | 0.5586     | 0.5131     | 0.7984     | 0.8044     | 0.7758     | 0.4037     |
| cosine_map@1         | 0.6476     | 0.1243     | 0.2956     | 0.6408     | 0.7358     | 0.6947     | 0.1815     |
| cosine_map@20        | 0.5299     | 0.4831     | 0.4209     | 0.4903     | 0.7407     | 0.7123     | 0.3267     |
| cosine_map@50        | 0.517      | 0.4269     | 0.3779     | 0.4683     | 0.7433     | 0.7152     | 0.3267     |
| cosine_map@100       | 0.5496     | 0.4303     | 0.3816     | 0.4974     | 0.7438     | 0.7157     | 0.3267     |
| cosine_map@150       | 0.558      | 0.445      | 0.3962     | 0.5056     | 0.7439     | 0.7158     | 0.3267     |
| cosine_map@200       | 0.561      | 0.4523     | 0.403      | 0.51       | 0.744      | 0.7158     | 0.3267     |
| cosine_map@500       | 0.5665     | 0.4644     | 0.4167     | 0.5152     | 0.7441     | 0.7159     | 0.3267     |

<!--
## 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: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 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: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 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: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 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: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 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: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 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`: 64
- `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`: 64
- `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   | -             | 0.6856                  | 0.5207                  | 0.4655                  | 0.6713                  | 0.6224                 | 0.5604                 | 0.5548                 |
| 0.0010 | 1    | 5.3354        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 0.1027 | 100  | 2.665         | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 0.2053 | 200  | 1.3375        | 0.7691                  | 0.6530                  | 0.6298                  | 0.7517                  | 0.7513                 | 0.7393                 | 0.5490                 |
| 0.3080 | 300  | 1.1101        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 0.4107 | 400  | 0.9453        | 0.7802                  | 0.6643                  | 0.6246                  | 0.7531                  | 0.7610                 | 0.7441                 | 0.5493                 |
| 0.5133 | 500  | 0.9202        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 0.6160 | 600  | 0.7887        | 0.7741                  | 0.6549                  | 0.6171                  | 0.7542                  | 0.7672                 | 0.7540                 | 0.5482                 |
| 0.7187 | 700  | 0.7604        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 0.8214 | 800  | 0.7219        | 0.7846                  | 0.6674                  | 0.6244                  | 0.7648                  | 0.7741                 | 0.7592                 | 0.5497                 |
| 0.9240 | 900  | 0.6965        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 1.0267 | 1000 | 0.6253        | 0.7646                  | 0.6391                  | 0.6122                  | 0.7503                  | 0.7825                 | 0.7704                 | 0.5463                 |
| 1.1294 | 1100 | 0.4737        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 1.2320 | 1200 | 0.5055        | 0.7758                  | 0.6582                  | 0.6178                  | 0.7514                  | 0.7857                 | 0.7764                 | 0.5501                 |
| 1.3347 | 1300 | 0.5042        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 1.4374 | 1400 | 0.5073        | 0.7613                  | 0.6578                  | 0.6178                  | 0.7505                  | 0.7829                 | 0.7762                 | 0.5452                 |
| 1.5400 | 1500 | 0.4975        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 1.6427 | 1600 | 0.5242        | 0.7736                  | 0.6673                  | 0.6279                  | 0.7555                  | 0.7940                 | 0.7859                 | 0.5477                 |
| 1.7454 | 1700 | 0.4713        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 1.8480 | 1800 | 0.4814        | 0.7845                  | 0.6733                  | 0.6285                  | 0.7642                  | 0.7992                 | 0.7904                 | 0.5449                 |
| 1.9507 | 1900 | 0.4526        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 2.0544 | 2000 | 0.36          | 0.7790                  | 0.6639                  | 0.6252                  | 0.7500                  | 0.8032                 | 0.7888                 | 0.5499                 |
| 2.1571 | 2100 | 0.3744        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 2.2598 | 2200 | 0.3031        | 0.7787                  | 0.6614                  | 0.6190                  | 0.7537                  | 0.7993                 | 0.7811                 | 0.5476                 |
| 2.3624 | 2300 | 0.3638        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 2.4651 | 2400 | 0.358         | 0.7798                  | 0.6615                  | 0.6258                  | 0.7497                  | 0.8018                 | 0.7828                 | 0.5481                 |
| 2.5678 | 2500 | 0.3247        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 2.6704 | 2600 | 0.3247        | 0.7854                  | 0.6663                  | 0.6248                  | 0.7560                  | 0.8081                 | 0.7835                 | 0.5452                 |
| 2.7731 | 2700 | 0.3263        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 2.8758 | 2800 | 0.3212        | 0.7761                  | 0.6681                  | 0.6250                  | 0.7517                  | 0.8121                 | 0.7927                 | 0.5458                 |
| 2.9784 | 2900 | 0.3291        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 3.0821 | 3000 | 0.2816        | 0.7727                  | 0.6604                  | 0.6163                  | 0.7370                  | 0.8163                 | 0.7985                 | 0.5473                 |
| 3.1848 | 3100 | 0.2698        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 3.2875 | 3200 | 0.2657        | 0.7757                  | 0.6615                  | 0.6247                  | 0.7417                  | 0.8117                 | 0.8004                 | 0.5436                 |
| 3.3901 | 3300 | 0.2724        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 3.4928 | 3400 | 0.2584        | 0.7850                  | 0.6583                  | 0.6320                  | 0.7458                  | 0.8120                 | 0.7980                 | 0.5454                 |
| 3.5955 | 3500 | 0.2573        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 3.6982 | 3600 | 0.2744        | 0.7796                  | 0.6552                  | 0.6237                  | 0.7409                  | 0.8193                 | 0.8018                 | 0.5466                 |
| 3.8008 | 3700 | 0.3054        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 3.9035 | 3800 | 0.2727        | 0.7825                  | 0.6642                  | 0.6293                  | 0.7504                  | 0.8213                 | 0.8058                 | 0.5463                 |
| 4.0062 | 3900 | 0.2353        | -                       | -                       | -                       | -                       | -                      | -                      | -                      |
| 4.1088 | 4000 | 0.2353        | 0.7747                  | 0.6628                  | 0.6263                  | 0.7384                  | 0.8239                 | 0.8065                 | 0.5447                 |


### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 4.1.0
- Transformers: 4.51.2
- 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.*
-->