checkpoint-4400/README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:124788
  - loss:GISTEmbedLoss
base_model: Alibaba-NLP/gte-multilingual-base
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 Alibaba-NLP/gte-multilingual-base
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full en
          type: full_en
        metrics:
          - type: cosine_accuracy@1
            value: 0.638095238095238
            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: 0.638095238095238
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.5157142857142857
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.3148571428571429
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.18980952380952382
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.1340952380952381
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.10433333333333333
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.06663116529391168
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.5440125491149368
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.7372320284968455
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.848443922949252
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.8860487771274941
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.9113100464031192
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.638095238095238
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.6935546556901672
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.7133251583573003
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.7690632647005352
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.7862144895240257
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.7968170592302795
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.638095238095238
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.805873015873016
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.805873015873016
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.805873015873016
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.805873015873016
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.805873015873016
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.638095238095238
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.5578685155173458
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.5473850321623162
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.581463340907654
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.5889169392279893
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.5925284111737003
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.5965656525880867
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full es
          type: full_es
        metrics:
          - type: cosine_accuracy@1
            value: 0.12972972972972974
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 1
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 1
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 1
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 1
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 1
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.12972972972972974
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.5721621621621621
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.3898378378378379
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.25248648648648647
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.19001801801801804
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.15216216216216216
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.0037413987812150314
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.38564412906376994
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.56634717829376
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.6751207657229007
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.7429721526766266
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.782741009344735
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.12972972972972974
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.6146062832951104
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.5888430944817052
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.6153911974508461
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.6488811790186049
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.668484227215925
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.12972972972972974
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.5603603603603604
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.5603603603603604
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.5603603603603604
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.5603603603603604
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.5603603603603604
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.12972972972972974
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.48065989256661584
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.4260414587944102
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.4313410890675031
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.44627409433309473
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.45409073457648325
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.4664141280463215
            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: 0.9704433497536946
            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: 0.5103448275862069
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.36581280788177345
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.24093596059113298
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.1805911330049261
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.14504926108374383
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.01108543831680986
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.3223233101463262
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.5039819404049483
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.6233745066729907
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.6835940274020903
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.7244154013186467
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.2955665024630542
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.5408722641900761
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.527886925844467
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.5577778671616822
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.5888462531918542
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.6086846330019594
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.2955665024630542
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.5113658734131055
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.5119042729281458
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.5119042729281458
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.5119471086531404
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.5119471086531404
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.2955665024630542
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.40262994538176794
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.3598095510459756
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.3640281449020211
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.3787945863322487
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.38618862635749335
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.3990240514562499
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: full zh
          type: full_zh
        metrics:
          - type: cosine_accuracy@1
            value: 0.6504854368932039
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.9805825242718447
            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: 0.6504854368932039
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.47766990291262146
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.2910679611650486
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.17669902912621357
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.12595469255663433
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.09839805825242721
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.060542712533387485
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.5114752810868121
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.6954673295380345
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.8032158798498642
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.846620542843508
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.8771023728333074
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.6504854368932039
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.6541147907794943
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.6727849863538982
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.7254296825073091
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.7444662716551141
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.7564060212104653
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.6504854368932039
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.8001618122977345
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.8004965963620132
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.8004965963620132
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.8004965963620132
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.8004965963620132
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.6504854368932039
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.5094545622745261
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.49522742290513777
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.5243132918013151
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.5319309142013369
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.5356726234545599
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.5407684120771897
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix es
          type: mix_es
        metrics:
          - type: cosine_accuracy@1
            value: 0.7264690587623505
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.9589183567342694
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.9791991679667187
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.9942797711908476
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.9963598543941757
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9973998959958398
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.7264690587623505
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.12420696827873114
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.051430057202288104
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.026245449817992726
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.017621771537528166
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.013286531461258454
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.2809028551618255
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.9175593690414283
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.9495839833593345
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.9700901369388107
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.9768157392962384
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.9820072802912115
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.7264690587623505
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.8030413573056574
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.811796736904274
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.816244308604025
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.8175588810577264
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.8184967672553575
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.7264690587623505
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.7950273648815123
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.7956778348360616
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.7959013329165427
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.7959172370306803
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.7959232938160362
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.7264690587623505
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.7336401935022089
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.7360366435506714
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.7366186564599716
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.7367425141591574
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.7368117834120087
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.7369173075310415
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix de
          type: mix_de
        metrics:
          - type: cosine_accuracy@1
            value: 0.6687467498699948
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 0.9495579823192928
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 0.9781591263650546
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 0.9864794591783671
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 0.9937597503900156
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 0.9947997919916797
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.6687467498699948
            name: Cosine Precision@1
          - type: cosine_precision@20
            value: 0.1250390015600624
            name: Cosine Precision@20
          - type: cosine_precision@50
            value: 0.05221008840353615
            name: Cosine Precision@50
          - type: cosine_precision@100
            value: 0.026718668746749875
            name: Cosine Precision@100
          - type: cosine_precision@150
            value: 0.017996186514127228
            name: Cosine Precision@150
          - type: cosine_precision@200
            value: 0.013546541861674468
            name: Cosine Precision@200
          - type: cosine_recall@1
            value: 0.2516640665626625
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 0.9084156699601317
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 0.9471138845553821
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 0.9683654012827179
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 0.9779857860981105
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 0.9813659213035187
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.6687467498699948
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.771957090473385
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.7827623591767751
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.7875734242708617
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.7894969663782526
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.7901321903376272
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.6687467498699948
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.7497638732138926
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.7507175554997805
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.7508323831532827
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.7508936641683207
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.7509002910567728
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.6687467498699948
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.6950013134615064
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.6978571886056382
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.6985915209847109
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.6987589388742937
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.6988064092994788
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.6989004605248843
            name: Cosine Map@500
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: mix zh
          type: mix_zh
        metrics:
          - type: cosine_accuracy@1
            value: 0.19240769630785232
            name: Cosine Accuracy@1
          - type: cosine_accuracy@20
            value: 1
            name: Cosine Accuracy@20
          - type: cosine_accuracy@50
            value: 1
            name: Cosine Accuracy@50
          - type: cosine_accuracy@100
            value: 1
            name: Cosine Accuracy@100
          - type: cosine_accuracy@150
            value: 1
            name: Cosine Accuracy@150
          - type: cosine_accuracy@200
            value: 1
            name: Cosine Accuracy@200
          - type: cosine_precision@1
            value: 0.19240769630785232
            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: 0.06196914543248396
            name: Cosine Recall@1
          - type: cosine_recall@20
            value: 1
            name: Cosine Recall@20
          - type: cosine_recall@50
            value: 1
            name: Cosine Recall@50
          - type: cosine_recall@100
            value: 1
            name: Cosine Recall@100
          - type: cosine_recall@150
            value: 1
            name: Cosine Recall@150
          - type: cosine_recall@200
            value: 1
            name: Cosine Recall@200
          - type: cosine_ndcg@1
            value: 0.19240769630785232
            name: Cosine Ndcg@1
          - type: cosine_ndcg@20
            value: 0.5476410654075157
            name: Cosine Ndcg@20
          - type: cosine_ndcg@50
            value: 0.5476410654075157
            name: Cosine Ndcg@50
          - type: cosine_ndcg@100
            value: 0.5476410654075157
            name: Cosine Ndcg@100
          - type: cosine_ndcg@150
            value: 0.5476410654075157
            name: Cosine Ndcg@150
          - type: cosine_ndcg@200
            value: 0.5476410654075157
            name: Cosine Ndcg@200
          - type: cosine_mrr@1
            value: 0.19240769630785232
            name: Cosine Mrr@1
          - type: cosine_mrr@20
            value: 0.40991240515421595
            name: Cosine Mrr@20
          - type: cosine_mrr@50
            value: 0.40991240515421595
            name: Cosine Mrr@50
          - type: cosine_mrr@100
            value: 0.40991240515421595
            name: Cosine Mrr@100
          - type: cosine_mrr@150
            value: 0.40991240515421595
            name: Cosine Mrr@150
          - type: cosine_mrr@200
            value: 0.40991240515421595
            name: Cosine Mrr@200
          - type: cosine_map@1
            value: 0.19240769630785232
            name: Cosine Map@1
          - type: cosine_map@20
            value: 0.3300676367396893
            name: Cosine Map@20
          - type: cosine_map@50
            value: 0.3300676367396893
            name: Cosine Map@50
          - type: cosine_map@100
            value: 0.3300676367396893
            name: Cosine Map@100
          - type: cosine_map@150
            value: 0.3300676367396893
            name: Cosine Map@150
          - type: cosine_map@200
            value: 0.3300676367396893
            name: Cosine Map@200
          - type: cosine_map@500
            value: 0.3300676367396893
            name: Cosine Map@500

SentenceTransformer based on Alibaba-NLP/gte-multilingual-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-multilingual-base on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 768-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: Alibaba-NLP/gte-multilingual-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Datasets:
  • full_en
  • full_de
  • full_es
  • full_zh
  • mix

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: NewModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'Volksvertreter',
    'Parlamentarier',
    'Oberbürgermeister',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Information Retrieval

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

Metric	full_en	full_es	full_de	full_zh	mix_es	mix_de	mix_zh
cosine_accuracy@1	0.6381	0.1297	0.2956	0.6505	0.7265	0.6687	0.1924
cosine_accuracy@20	0.9905	1.0	0.9704	0.9806	0.9589	0.9496	1.0
cosine_accuracy@50	0.9905	1.0	0.9852	0.9903	0.9792	0.9782	1.0
cosine_accuracy@100	0.9905	1.0	0.9852	0.9903	0.9943	0.9865	1.0
cosine_accuracy@150	0.9905	1.0	0.9901	0.9903	0.9964	0.9938	1.0
cosine_accuracy@200	0.9905	1.0	0.9901	0.9903	0.9974	0.9948	1.0
cosine_precision@1	0.6381	0.1297	0.2956	0.6505	0.7265	0.6687	0.1924
cosine_precision@20	0.5157	0.5722	0.5103	0.4777	0.1242	0.125	0.1544
cosine_precision@50	0.3149	0.3898	0.3658	0.2911	0.0514	0.0522	0.0618
cosine_precision@100	0.1898	0.2525	0.2409	0.1767	0.0262	0.0267	0.0309
cosine_precision@150	0.1341	0.19	0.1806	0.126	0.0176	0.018	0.0206
cosine_precision@200	0.1043	0.1522	0.145	0.0984	0.0133	0.0135	0.0154
cosine_recall@1	0.0666	0.0037	0.0111	0.0605	0.2809	0.2517	0.062
cosine_recall@20	0.544	0.3856	0.3223	0.5115	0.9176	0.9084	1.0
cosine_recall@50	0.7372	0.5663	0.504	0.6955	0.9496	0.9471	1.0
cosine_recall@100	0.8484	0.6751	0.6234	0.8032	0.9701	0.9684	1.0
cosine_recall@150	0.886	0.743	0.6836	0.8466	0.9768	0.978	1.0
cosine_recall@200	0.9113	0.7827	0.7244	0.8771	0.982	0.9814	1.0
cosine_ndcg@1	0.6381	0.1297	0.2956	0.6505	0.7265	0.6687	0.1924
cosine_ndcg@20	0.6936	0.6146	0.5409	0.6541	0.803	0.772	0.5476
cosine_ndcg@50	0.7133	0.5888	0.5279	0.6728	0.8118	0.7828	0.5476
cosine_ndcg@100	0.7691	0.6154	0.5578	0.7254	0.8162	0.7876	0.5476
cosine_ndcg@150	0.7862	0.6489	0.5888	0.7445	0.8176	0.7895	0.5476
cosine_ndcg@200	0.7968	0.6685	0.6087	0.7564	0.8185	0.7901	0.5476
cosine_mrr@1	0.6381	0.1297	0.2956	0.6505	0.7265	0.6687	0.1924
cosine_mrr@20	0.8059	0.5604	0.5114	0.8002	0.795	0.7498	0.4099
cosine_mrr@50	0.8059	0.5604	0.5119	0.8005	0.7957	0.7507	0.4099
cosine_mrr@100	0.8059	0.5604	0.5119	0.8005	0.7959	0.7508	0.4099
cosine_mrr@150	0.8059	0.5604	0.5119	0.8005	0.7959	0.7509	0.4099
cosine_mrr@200	0.8059	0.5604	0.5119	0.8005	0.7959	0.7509	0.4099
cosine_map@1	0.6381	0.1297	0.2956	0.6505	0.7265	0.6687	0.1924
cosine_map@20	0.5579	0.4807	0.4026	0.5095	0.7336	0.695	0.3301
cosine_map@50	0.5474	0.426	0.3598	0.4952	0.736	0.6979	0.3301
cosine_map@100	0.5815	0.4313	0.364	0.5243	0.7366	0.6986	0.3301
cosine_map@150	0.5889	0.4463	0.3788	0.5319	0.7367	0.6988	0.3301
cosine_map@200	0.5925	0.4541	0.3862	0.5357	0.7368	0.6988	0.3301
cosine_map@500	0.5966	0.4664	0.399	0.5408	0.7369	0.6989	0.3301

Training Details

Training Datasets

full_en

full_en

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

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 5.68 tokens max: 11 tokens	min: 3 tokens mean: 5.76 tokens max: 12 tokens

• Samples:

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

• Loss: GISTEmbedLoss with these parameters:

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

full_de

full_de

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

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 7.99 tokens max: 30 tokens	min: 3 tokens mean: 8.19 tokens max: 30 tokens

• Samples:

  anchor	positive
  Staffelkommandantin	Kommodore
  Luftwaffenoffizierin	Luftwaffenoffizier/Luftwaffenoffizierin
  Staffelkommandantin	Luftwaffenoffizierin

• Loss: GISTEmbedLoss with these parameters:

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

full_es

full_es

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

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 9.13 tokens max: 32 tokens	min: 3 tokens mean: 8.84 tokens max: 32 tokens

• Samples:

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

• Loss: GISTEmbedLoss with these parameters:

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

full_zh

full_zh

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

  	anchor	positive
  type	string	string
  details	min: 5 tokens mean: 7.15 tokens max: 14 tokens	min: 5 tokens mean: 7.46 tokens max: 21 tokens

• Samples:

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

• Loss: GISTEmbedLoss with these parameters:

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

mix

mix

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

  	anchor	positive
  type	string	string
  details	min: 2 tokens mean: 6.71 tokens max: 19 tokens	min: 2 tokens mean: 7.69 tokens max: 19 tokens

• Samples:

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

• Loss: GISTEmbedLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 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

Click to expand

• 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

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	-	0.7447	0.6125	0.5378	0.7240	0.7029	0.6345	0.5531
0.0010	1	3.4866	-	-	-	-	-	-	-
0.1027	100	2.5431	-	-	-	-	-	-	-
0.2053	200	1.4536	0.7993	0.6633	0.5974	0.7642	0.7567	0.7011	0.5498
0.3080	300	1.1018	-	-	-	-	-	-	-
0.4107	400	0.9184	0.7925	0.6586	0.6058	0.7587	0.7749	0.7278	0.5486
0.5133	500	0.8973	-	-	-	-	-	-	-
0.6160	600	0.7309	0.7951	0.6671	0.6096	0.7708	0.7793	0.7339	0.5525
0.7187	700	0.7297	-	-	-	-	-	-	-
0.8214	800	0.7281	0.7929	0.6711	0.6088	0.7645	0.7899	0.7444	0.5479
0.9240	900	0.6607	-	-	-	-	-	-	-
1.0267	1000	0.6075	0.7915	0.6659	0.6088	0.7665	0.7968	0.7588	0.5482
1.1294	1100	0.4553	-	-	-	-	-	-	-
1.2320	1200	0.4775	0.7979	0.6696	0.6033	0.7669	0.7959	0.7624	0.5484
1.3347	1300	0.4838	-	-	-	-	-	-	-
1.4374	1400	0.4912	0.7973	0.6757	0.6112	0.7656	0.7978	0.7650	0.5487
1.5400	1500	0.4732	-	-	-	-	-	-	-
1.6427	1600	0.5269	0.8031	0.6723	0.6108	0.7654	0.8008	0.7660	0.5492
1.7454	1700	0.4822	-	-	-	-	-	-	-
1.8480	1800	0.5072	0.7962	0.6668	0.6051	0.7592	0.8001	0.7714	0.5486
1.9507	1900	0.4709	-	-	-	-	-	-	-
2.0544	2000	0.3772	0.7940	0.6647	0.6037	0.7579	0.8064	0.7732	0.5479
2.1571	2100	0.3982	-	-	-	-	-	-	-
2.2598	2200	0.3073	0.7969	0.6652	0.6005	0.7625	0.8054	0.7734	0.5493
2.3624	2300	0.383	-	-	-	-	-	-	-
2.4651	2400	0.3687	0.7925	0.6690	0.5987	0.7583	0.8081	0.7735	0.5477
2.5678	2500	0.3472	-	-	-	-	-	-	-
2.6704	2600	0.3557	0.7956	0.6758	0.6019	0.7659	0.8082	0.7767	0.5491
2.7731	2700	0.3527	-	-	-	-	-	-	-
2.8758	2800	0.3446	0.7945	0.6719	0.6020	0.7616	0.8124	0.7818	0.5496
2.9784	2900	0.3566	-	-	-	-	-	-	-
3.0821	3000	0.3252	0.7948	0.6682	0.6025	0.7617	0.8152	0.7848	0.5516
3.1848	3100	0.2968	-	-	-	-	-	-	-
3.2875	3200	0.2962	0.7953	0.6717	0.6086	0.7613	0.8110	0.7824	0.5482
3.3901	3300	0.3084	-	-	-	-	-	-	-
3.4928	3400	0.2909	0.7940	0.6634	0.6023	0.7615	0.8138	0.7822	0.5457
3.5955	3500	0.2964	-	-	-	-	-	-	-
3.6982	3600	0.3193	0.7960	0.6635	0.6070	0.7534	0.8164	0.7844	0.5467
3.8008	3700	0.3514	-	-	-	-	-	-	-
3.9035	3800	0.3147	0.7973	0.6696	0.6125	0.7616	0.8176	0.7885	0.5469
4.0062	3900	0.2738	-	-	-	-	-	-	-
4.1088	4000	0.2842	0.7960	0.6672	0.6082	0.7536	0.8174	0.7891	0.5479
4.2115	4100	0.2739	-	-	-	-	-	-	-
4.3142	4200	0.2704	0.7979	0.6681	0.6111	0.7540	0.8180	0.7891	0.5476
4.4168	4300	0.2529	-	-	-	-	-	-	-
4.5195	4400	0.272	0.7968	0.6685	0.6087	0.7564	0.8185	0.7901	0.5476

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

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

GISTEmbedLoss

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