--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:86648 - loss:MSELoss widget: - source_sentence: Familienberaterin sentences: - electric power station operator - venue booker & promoter - betrieblicher Aus- und Weiterbildner/betriebliche Aus- und Weiterbildnerin - source_sentence: high school RS teacher sentences: - infantryman - Schnellbedienungsrestaurantteamleiter - drill setup operator - source_sentence: lighting designer sentences: - software support manager - 直升机维护协调员 - bus maintenance supervisor - source_sentence: 机场消防员 sentences: - Flake操作员 - técnico en gestión de residuos peligrosos/técnica en gestión de residuos peligrosos - 专门学校老师 - source_sentence: Entwicklerin für mobile Anwendungen sentences: - fashion design expert - Mergers-and-Acquisitions-Analyst/Mergers-and-Acquisitions-Analystin - commercial bid manager 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 results: - task: type: information-retrieval name: Information Retrieval dataset: name: full en type: full_en metrics: - type: cosine_accuracy@1 value: 0.6285714285714286 name: Cosine Accuracy@1 - type: cosine_accuracy@20 value: 0.9714285714285714 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: 0.6285714285714286 name: Cosine Precision@1 - type: cosine_precision@20 value: 0.4723809523809524 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.2838095238095238 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.1706666666666667 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.12285714285714286 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.09700000000000002 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.06568451704213447 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.5041312032991911 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.6762963371727007 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.7798036464336738 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.8311908383371492 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.8655400214018215 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.6285714285714286 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.6385286667884668 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.6505087993598385 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.7009585791000247 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.7228549618650749 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.7370730818153396 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.6285714285714286 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.7790726817042607 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.7797979143260452 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.7797979143260452 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.7797979143260452 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.7797979143260452 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.6285714285714286 name: Cosine Map@1 - type: cosine_map@20 value: 0.4949002324392317 name: Cosine Map@20 - type: cosine_map@50 value: 0.47542864021103454 name: Cosine Map@50 - type: cosine_map@100 value: 0.5027685735699932 name: Cosine Map@100 - type: cosine_map@150 value: 0.5108956115342047 name: Cosine Map@150 - type: cosine_map@200 value: 0.5152152246235047 name: Cosine Map@200 - type: cosine_map@500 value: 0.5211733943510876 name: Cosine Map@500 - task: type: information-retrieval name: Information Retrieval dataset: name: full es type: full_es metrics: - type: cosine_accuracy@1 value: 0.11351351351351352 name: Cosine Accuracy@1 - type: cosine_accuracy@20 value: 1.0 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 1.0 name: Cosine Accuracy@50 - type: cosine_accuracy@100 value: 1.0 name: Cosine Accuracy@100 - type: cosine_accuracy@150 value: 1.0 name: Cosine Accuracy@150 - type: cosine_accuracy@200 value: 1.0 name: Cosine Accuracy@200 - type: cosine_precision@1 value: 0.11351351351351352 name: Cosine Precision@1 - type: cosine_precision@20 value: 0.5213513513513512 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.33891891891891895 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.2141081081081081 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.16104504504504505 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.13094594594594594 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.0035045234969014166 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.34830621955762764 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.5043797869988105 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.5962566893615484 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.6539916045900668 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.7027707655811134 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.11351351351351352 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.5638160555705326 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.5286289587475489 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.5494533442820461 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.5778904564772578 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.6002374248801999 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.11351351351351352 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.55 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.55 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.55 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.55 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.55 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.11351351351351352 name: Cosine Map@1 - type: cosine_map@20 value: 0.4321212731877681 name: Cosine Map@20 - type: cosine_map@50 value: 0.3662438776904182 name: Cosine Map@50 - type: cosine_map@100 value: 0.3676467044477579 name: Cosine Map@100 - type: cosine_map@150 value: 0.37914071893635704 name: Cosine Map@150 - type: cosine_map@200 value: 0.3864291047810966 name: Cosine Map@200 - type: cosine_map@500 value: 0.3967448814407886 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: 0.9605911330049262 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 0.9802955665024631 name: Cosine Accuracy@50 - type: cosine_accuracy@100 value: 0.9852216748768473 name: Cosine Accuracy@100 - type: cosine_accuracy@150 value: 0.9852216748768473 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: 0.424384236453202 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.29064039408866993 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.19019704433497536 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.14476190476190476 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.1177832512315271 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.01108543831680986 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.2623989771425487 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.399936827395569 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.5011599542158983 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.5599024076006294 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.6019565140878311 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.2955665024630542 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.46461290935992494 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.43636700085765784 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.4594232150790335 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.4887319216460325 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.5085159310260775 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.2955665024630542 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.503435229891329 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.5041035247761447 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.5041884576791513 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.5041884576791513 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.5042166068698621 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.2955665024630542 name: Cosine Map@1 - type: cosine_map@20 value: 0.3326012942578798 name: Cosine Map@20 - type: cosine_map@50 value: 0.2779781159809199 name: Cosine Map@50 - type: cosine_map@100 value: 0.27530357902528746 name: Cosine Map@100 - type: cosine_map@150 value: 0.2859029789549631 name: Cosine Map@150 - type: cosine_map@200 value: 0.29192358526577794 name: Cosine Map@200 - type: cosine_map@500 value: 0.3037728006457777 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: 0.970873786407767 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 0.9805825242718447 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: 0.4461165048543689 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.26932038834951455 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.16601941747572818 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.12000000000000002 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.09475728155339808 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.06125809321810901 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.4798173076061309 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.6511259115267456 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.7667280032499174 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.8234348132226993 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.8570886860782638 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.6504854368932039 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.6163434250133266 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.6306194061713684 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.6852740031621496 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.7087858531025408 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.7227726687256436 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.6504854368932039 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.7938511326860843 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.7941135310067349 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.7943002375041209 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.7943002375041209 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.7943002375041209 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.6504854368932039 name: Cosine Map@1 - type: cosine_map@20 value: 0.4673451367444491 name: Cosine Map@20 - type: cosine_map@50 value: 0.4491601687897158 name: Cosine Map@50 - type: cosine_map@100 value: 0.4759775327060125 name: Cosine Map@100 - type: cosine_map@150 value: 0.484283864447002 name: Cosine Map@150 - type: cosine_map@200 value: 0.4885403171787604 name: Cosine Map@200 - type: cosine_map@500 value: 0.4948931148880558 name: Cosine Map@500 - task: type: information-retrieval name: Information Retrieval dataset: name: mix es type: mix_es metrics: - type: cosine_accuracy@1 value: 0.6172646905876235 name: Cosine Accuracy@1 - type: cosine_accuracy@20 value: 0.9032761310452418 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 0.9443577743109725 name: Cosine Accuracy@50 - type: cosine_accuracy@100 value: 0.9703588143525741 name: Cosine Accuracy@100 - type: cosine_accuracy@150 value: 0.9812792511700468 name: Cosine Accuracy@150 - type: cosine_accuracy@200 value: 0.9859594383775351 name: Cosine Accuracy@200 - type: cosine_precision@1 value: 0.6172646905876235 name: Cosine Precision@1 - type: cosine_precision@20 value: 0.10972438897555903 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.04786271450858035 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.025169006760270413 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.017157219622118216 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.013018720748829957 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.2379838050664884 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.8149369784315182 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.8866788004853527 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.9331773270930838 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.9536141445657828 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.9651759403709481 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.6172646905876235 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.6863945449619185 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.7059805315894592 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.7161349937562115 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.7201494083175249 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.722225937142632 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.6172646905876235 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.6921361840847764 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.6935275501084183 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.6938924919697613 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.6939819360030616 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.6940082129440573 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.6172646905876235 name: Cosine Map@1 - type: cosine_map@20 value: 0.6028333286973904 name: Cosine Map@20 - type: cosine_map@50 value: 0.6079882517976847 name: Cosine Map@50 - type: cosine_map@100 value: 0.6094136625128228 name: Cosine Map@100 - type: cosine_map@150 value: 0.6097807307495342 name: Cosine Map@150 - type: cosine_map@200 value: 0.6099278426294548 name: Cosine Map@200 - type: cosine_map@500 value: 0.6101218939355526 name: Cosine Map@500 - task: type: information-retrieval name: Information Retrieval dataset: name: mix de type: mix_de metrics: - type: cosine_accuracy@1 value: 0.5429017160686428 name: Cosine Accuracy@1 - type: cosine_accuracy@20 value: 0.8725949037961519 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 0.9297971918876755 name: Cosine Accuracy@50 - type: cosine_accuracy@100 value: 0.9552782111284451 name: Cosine Accuracy@100 - type: cosine_accuracy@150 value: 0.968278731149246 name: Cosine Accuracy@150 - type: cosine_accuracy@200 value: 0.9729589183567343 name: Cosine Accuracy@200 - type: cosine_precision@1 value: 0.5429017160686428 name: Cosine Precision@1 - type: cosine_precision@20 value: 0.10709828393135724 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.04726989079563183 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.025002600104004166 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.01712601837406829 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.013044721788871557 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.20383948691280984 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.7817386028774485 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.8605044201768071 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.9077223088923557 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.9319032761310452 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.9461778471138845 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.5429017160686428 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.6364696194038222 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.6580204683537704 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.6686859699628315 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.6734670399055159 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.6761041848609185 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.5429017160686428 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.6331176720726237 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.6350347522721764 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.6354157777188323 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.6355194502419383 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.635546462249249 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.5429017160686428 name: Cosine Map@1 - type: cosine_map@20 value: 0.546038259426052 name: Cosine Map@20 - type: cosine_map@50 value: 0.5513401593649401 name: Cosine Map@50 - type: cosine_map@100 value: 0.5528890114435938 name: Cosine Map@100 - type: cosine_map@150 value: 0.5533285819634786 name: Cosine Map@150 - type: cosine_map@200 value: 0.5535297820757661 name: Cosine Map@200 - type: cosine_map@500 value: 0.5538215020153545 name: Cosine Map@500 - task: type: information-retrieval name: Information Retrieval dataset: name: mix zh type: mix_zh metrics: - type: cosine_accuracy@1 value: 0.5751565762004175 name: Cosine Accuracy@1 - type: cosine_accuracy@20 value: 0.9514613778705637 name: Cosine Accuracy@20 - type: cosine_accuracy@50 value: 0.975991649269311 name: Cosine Accuracy@50 - type: cosine_accuracy@100 value: 0.9848643006263048 name: Cosine Accuracy@100 - type: cosine_accuracy@150 value: 0.9895615866388309 name: Cosine Accuracy@150 - type: cosine_accuracy@200 value: 0.9916492693110647 name: Cosine Accuracy@200 - type: cosine_precision@1 value: 0.5751565762004175 name: Cosine Precision@1 - type: cosine_precision@20 value: 0.123982254697286 name: Cosine Precision@20 - type: cosine_precision@50 value: 0.05465553235908143 name: Cosine Precision@50 - type: cosine_precision@100 value: 0.02851252609603341 name: Cosine Precision@100 - type: cosine_precision@150 value: 0.019324982602644397 name: Cosine Precision@150 - type: cosine_precision@200 value: 0.014634655532359089 name: Cosine Precision@200 - type: cosine_recall@1 value: 0.19298513768764292 name: Cosine Recall@1 - type: cosine_recall@20 value: 0.8174060542797494 name: Cosine Recall@20 - type: cosine_recall@50 value: 0.901000347947112 name: Cosine Recall@50 - type: cosine_recall@100 value: 0.9399095337508698 name: Cosine Recall@100 - type: cosine_recall@150 value: 0.9558716075156575 name: Cosine Recall@150 - type: cosine_recall@200 value: 0.965196590118302 name: Cosine Recall@200 - type: cosine_ndcg@1 value: 0.5751565762004175 name: Cosine Ndcg@1 - type: cosine_ndcg@20 value: 0.6621196118161056 name: Cosine Ndcg@20 - type: cosine_ndcg@50 value: 0.6858570871515306 name: Cosine Ndcg@50 - type: cosine_ndcg@100 value: 0.6947962879201968 name: Cosine Ndcg@100 - type: cosine_ndcg@150 value: 0.6980250427797421 name: Cosine Ndcg@150 - type: cosine_ndcg@200 value: 0.6997922044919449 name: Cosine Ndcg@200 - type: cosine_mrr@1 value: 0.5751565762004175 name: Cosine Mrr@1 - type: cosine_mrr@20 value: 0.6974988781113621 name: Cosine Mrr@20 - type: cosine_mrr@50 value: 0.6983413027160801 name: Cosine Mrr@50 - type: cosine_mrr@100 value: 0.6984820179753005 name: Cosine Mrr@100 - type: cosine_mrr@150 value: 0.6985228351798531 name: Cosine Mrr@150 - type: cosine_mrr@200 value: 0.6985351624205532 name: Cosine Mrr@200 - type: cosine_map@1 value: 0.5751565762004175 name: Cosine Map@1 - type: cosine_map@20 value: 0.5395939445358217 name: Cosine Map@20 - type: cosine_map@50 value: 0.5465541726714618 name: Cosine Map@50 - type: cosine_map@100 value: 0.5480058234906587 name: Cosine Map@100 - type: cosine_map@150 value: 0.5483452539266979 name: Cosine Map@150 - type: cosine_map@200 value: 0.548487754480418 name: Cosine Map@200 - type: cosine_map@500 value: 0.5486704400924459 name: Cosine Map@500 --- # SentenceTransformer This is a [sentence-transformers](https://www.SBERT.net) model trained. 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 - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### 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: 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: ```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 = [ 'Entwicklerin für mobile Anwendungen', 'Mergers-and-Acquisitions-Analyst/Mergers-and-Acquisitions-Analystin', 'fashion design expert', ] 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](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 | 0.6286 | 0.1135 | 0.2956 | 0.6505 | 0.6173 | 0.5429 | 0.5752 | | cosine_accuracy@20 | 0.9714 | 1.0 | 0.9606 | 0.9709 | 0.9033 | 0.8726 | 0.9515 | | cosine_accuracy@50 | 0.9905 | 1.0 | 0.9803 | 0.9806 | 0.9444 | 0.9298 | 0.976 | | cosine_accuracy@100 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9704 | 0.9553 | 0.9849 | | cosine_accuracy@150 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9813 | 0.9683 | 0.9896 | | cosine_accuracy@200 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.986 | 0.973 | 0.9916 | | cosine_precision@1 | 0.6286 | 0.1135 | 0.2956 | 0.6505 | 0.6173 | 0.5429 | 0.5752 | | cosine_precision@20 | 0.4724 | 0.5214 | 0.4244 | 0.4461 | 0.1097 | 0.1071 | 0.124 | | cosine_precision@50 | 0.2838 | 0.3389 | 0.2906 | 0.2693 | 0.0479 | 0.0473 | 0.0547 | | cosine_precision@100 | 0.1707 | 0.2141 | 0.1902 | 0.166 | 0.0252 | 0.025 | 0.0285 | | cosine_precision@150 | 0.1229 | 0.161 | 0.1448 | 0.12 | 0.0172 | 0.0171 | 0.0193 | | cosine_precision@200 | 0.097 | 0.1309 | 0.1178 | 0.0948 | 0.013 | 0.013 | 0.0146 | | cosine_recall@1 | 0.0657 | 0.0035 | 0.0111 | 0.0613 | 0.238 | 0.2038 | 0.193 | | cosine_recall@20 | 0.5041 | 0.3483 | 0.2624 | 0.4798 | 0.8149 | 0.7817 | 0.8174 | | cosine_recall@50 | 0.6763 | 0.5044 | 0.3999 | 0.6511 | 0.8867 | 0.8605 | 0.901 | | cosine_recall@100 | 0.7798 | 0.5963 | 0.5012 | 0.7667 | 0.9332 | 0.9077 | 0.9399 | | cosine_recall@150 | 0.8312 | 0.654 | 0.5599 | 0.8234 | 0.9536 | 0.9319 | 0.9559 | | cosine_recall@200 | 0.8655 | 0.7028 | 0.602 | 0.8571 | 0.9652 | 0.9462 | 0.9652 | | cosine_ndcg@1 | 0.6286 | 0.1135 | 0.2956 | 0.6505 | 0.6173 | 0.5429 | 0.5752 | | cosine_ndcg@20 | 0.6385 | 0.5638 | 0.4646 | 0.6163 | 0.6864 | 0.6365 | 0.6621 | | cosine_ndcg@50 | 0.6505 | 0.5286 | 0.4364 | 0.6306 | 0.706 | 0.658 | 0.6859 | | cosine_ndcg@100 | 0.701 | 0.5495 | 0.4594 | 0.6853 | 0.7161 | 0.6687 | 0.6948 | | cosine_ndcg@150 | 0.7229 | 0.5779 | 0.4887 | 0.7088 | 0.7201 | 0.6735 | 0.698 | | **cosine_ndcg@200** | **0.7371** | **0.6002** | **0.5085** | **0.7228** | **0.7222** | **0.6761** | **0.6998** | | cosine_mrr@1 | 0.6286 | 0.1135 | 0.2956 | 0.6505 | 0.6173 | 0.5429 | 0.5752 | | cosine_mrr@20 | 0.7791 | 0.55 | 0.5034 | 0.7939 | 0.6921 | 0.6331 | 0.6975 | | cosine_mrr@50 | 0.7798 | 0.55 | 0.5041 | 0.7941 | 0.6935 | 0.635 | 0.6983 | | cosine_mrr@100 | 0.7798 | 0.55 | 0.5042 | 0.7943 | 0.6939 | 0.6354 | 0.6985 | | cosine_mrr@150 | 0.7798 | 0.55 | 0.5042 | 0.7943 | 0.694 | 0.6355 | 0.6985 | | cosine_mrr@200 | 0.7798 | 0.55 | 0.5042 | 0.7943 | 0.694 | 0.6355 | 0.6985 | | cosine_map@1 | 0.6286 | 0.1135 | 0.2956 | 0.6505 | 0.6173 | 0.5429 | 0.5752 | | cosine_map@20 | 0.4949 | 0.4321 | 0.3326 | 0.4673 | 0.6028 | 0.546 | 0.5396 | | cosine_map@50 | 0.4754 | 0.3662 | 0.278 | 0.4492 | 0.608 | 0.5513 | 0.5466 | | cosine_map@100 | 0.5028 | 0.3676 | 0.2753 | 0.476 | 0.6094 | 0.5529 | 0.548 | | cosine_map@150 | 0.5109 | 0.3791 | 0.2859 | 0.4843 | 0.6098 | 0.5533 | 0.5483 | | cosine_map@200 | 0.5152 | 0.3864 | 0.2919 | 0.4885 | 0.6099 | 0.5535 | 0.5485 | | cosine_map@500 | 0.5212 | 0.3967 | 0.3038 | 0.4949 | 0.6101 | 0.5538 | 0.5487 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 86,648 training samples * Columns: sentence and label * Approximate statistics based on the first 1000 samples: | | sentence | label | |:--------|:---------------------------------------------------------------------------------|:-------------------------------------| | type | string | list | | details | | | * Samples: | sentence | label | |:-----------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------| | | [-0.07171934843063354, 0.03595816716551781, -0.029780959710478783, 0.006593302357941866, 0.040611181408166885, ...] | | airport environment officer | [-0.022075481712818146, 0.02999737113714218, -0.02189866080880165, 0.016531817615032196, 0.012234307825565338, ...] | | Flake操作员 | [-0.04815564677119255, 0.023524893447756767, -0.01583661139011383, 0.042527906596660614, 0.03815540298819542, ...] | * Loss: [MSELoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss) ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `gradient_accumulation_steps`: 2 - `learning_rate`: 0.0001 - `num_train_epochs`: 5 - `warmup_ratio`: 0.05 - `log_on_each_node`: False - `fp16`: True - `dataloader_num_workers`: 4 - `ddp_find_unused_parameters`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 2 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 0.0001 - `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 | - | 0.5348 | 0.4311 | 0.3678 | 0.5333 | 0.2580 | 0.1924 | 0.2871 | | 0.0030 | 1 | 0.0017 | - | - | - | - | - | - | - | | 0.2959 | 100 | 0.001 | - | - | - | - | - | - | - | | 0.5917 | 200 | 0.0005 | 0.6702 | 0.5287 | 0.4566 | 0.6809 | 0.5864 | 0.5302 | 0.4739 | | 0.8876 | 300 | 0.0004 | - | - | - | - | - | - | - | | 1.1834 | 400 | 0.0004 | 0.7057 | 0.5643 | 0.4790 | 0.7033 | 0.6604 | 0.6055 | 0.6003 | | 1.4793 | 500 | 0.0004 | - | - | - | - | - | - | - | | 1.7751 | 600 | 0.0003 | 0.7184 | 0.5783 | 0.4910 | 0.7127 | 0.6927 | 0.6416 | 0.6485 | | 2.0710 | 700 | 0.0003 | - | - | - | - | - | - | - | | 2.3669 | 800 | 0.0003 | 0.7307 | 0.5938 | 0.5023 | 0.7233 | 0.7125 | 0.6639 | 0.6847 | | 2.6627 | 900 | 0.0003 | - | - | - | - | - | - | - | | 2.9586 | 1000 | 0.0003 | 0.7371 | 0.6002 | 0.5085 | 0.7228 | 0.7222 | 0.6761 | 0.6998 | ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 4.1.0 - Transformers: 4.51.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.6.0 - Datasets: 3.5.0 - Tokenizers: 0.21.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MSELoss ```bibtex @inproceedings{reimers-2020-multilingual-sentence-bert, title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2020", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/2004.09813", } ```