metadata
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: 0.47238095238095235
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.28514285714285714
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.17142857142857143
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.12361904761904763
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.09742857142857143
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.06568451704213447
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.5028457675067052
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.676933903111657
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.7837663267176828
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.8369671671626038
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.8683370262861448
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.6285714285714286
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6393119319266262
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6526673690626589
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.7043574282251062
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7269332569198788
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.7401982784576455
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.6285714285714286
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.7822472848788637
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.7830464856780646
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.7830464856780646
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.7830464856780646
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.7830464856780646
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.6285714285714286
name: Cosine Map@1
- type: cosine_map@20
value: 0.49537416609793716
name: Cosine Map@20
- type: cosine_map@50
value: 0.47813955037924555
name: Cosine Map@50
- type: cosine_map@100
value: 0.5059345967521239
name: Cosine Map@100
- type: cosine_map@150
value: 0.5144312336524836
name: Cosine Map@150
- type: cosine_map@200
value: 0.5185744183980712
name: Cosine Map@200
- type: cosine_map@500
value: 0.5244908168836407
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
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: 0.11351351351351352
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.5251351351351352
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.34075675675675676
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.21718918918918914
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.1633873873873874
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.13205405405405404
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.0034752702480554325
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.3545024062351768
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.5069144726976866
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.6025543668510833
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.6642981040735876
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.7089070977578413
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.11351351351351352
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.5689965277663172
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.5323465786773958
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.5554442013067378
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.5850845990402996
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.60586753818696
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.11351351351351352
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.5504504504504504
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.5504504504504504
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.5504504504504504
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.5504504504504504
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.5504504504504504
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.11351351351351352
name: Cosine Map@1
- type: cosine_map@20
value: 0.4359197027223551
name: Cosine Map@20
- type: cosine_map@50
value: 0.3706456082465585
name: Cosine Map@50
- type: cosine_map@100
value: 0.3732010932885098
name: Cosine Map@100
- type: cosine_map@150
value: 0.38519119117400524
name: Cosine Map@150
- type: cosine_map@200
value: 0.39213165533322514
name: Cosine Map@200
- type: cosine_map@500
value: 0.4025485639452067
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: 0.9753694581280788
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9901477832512315
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: 0.4224137931034483
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.29339901477832514
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.19157635467980297
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.1463711001642036
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.11795566502463055
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.01108543831680986
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.26144279274804777
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.403029076454949
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.5037011732756571
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.5665263476845617
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.6046168597504225
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.2955665024630542
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.46432363286716843
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.4395352032741748
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.4621140849129699
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.4930797052274761
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.5108824775097222
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.2955665024630542
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.5051277902045789
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.5052574246354837
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.5054486024547283
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.5054486024547283
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.5054486024547283
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.2955665024630542
name: Cosine Map@1
- type: cosine_map@20
value: 0.3324304850209341
name: Cosine Map@20
- type: cosine_map@50
value: 0.28114451704276633
name: Cosine Map@50
- type: cosine_map@100
value: 0.2779170965376895
name: Cosine Map@100
- type: cosine_map@150
value: 0.28901327518126896
name: Cosine Map@150
- type: cosine_map@200
value: 0.2944583316893818
name: Cosine Map@200
- type: cosine_map@500
value: 0.3065620295728344
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: full zh
type: full_zh
metrics:
- type: cosine_accuracy@1
value: 0.6601941747572816
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.970873786407767
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: 0.6601941747572816
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.44466019417475733
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.2700970873786408
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.16611650485436893
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.11993527508090616
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.0950970873786408
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.06611246215014785
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.48241403320688186
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.6545173174336991
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.7666222988041391
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.821433115232699
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.8607757081755069
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.6601941747572816
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6200439246564962
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6357468583118394
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.6892184385347752
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7120690440507333
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.7279251789627177
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.6601941747572816
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.802674662097849
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.8031466146329083
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.8031466146329083
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.8031466146329083
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.8031466146329083
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.6601941747572816
name: Cosine Map@1
- type: cosine_map@20
value: 0.47064044627994783
name: Cosine Map@20
- type: cosine_map@50
value: 0.454032660512398
name: Cosine Map@50
- type: cosine_map@100
value: 0.48053939417933
name: Cosine Map@100
- type: cosine_map@150
value: 0.488614341849449
name: Cosine Map@150
- type: cosine_map@200
value: 0.49318512356249333
name: Cosine Map@200
- type: cosine_map@500
value: 0.4992400242495022
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix es
type: mix_es
metrics:
- type: cosine_accuracy@1
value: 0.62402496099844
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9084763390535622
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9448777951118045
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9708788351534061
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9812792511700468
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9890795631825273
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.62402496099844
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.11081643265730629
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.048185127405096215
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.02523140925637026
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.017181487259490376
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.013039521580863236
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.24088725453780055
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.8230146348711092
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.8927890448951292
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.9353440804298839
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.9547581903276131
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.9665453284798058
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.62402496099844
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6941478214145459
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.7132300033054162
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.7225477562617905
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7263840213327514
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.7285011388972827
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.62402496099844
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.6980879020274213
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.6993358208254645
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.6997194206976989
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.6998094104858287
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.699853804444636
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.62402496099844
name: Cosine Map@1
- type: cosine_map@20
value: 0.6113400845323398
name: Cosine Map@20
- type: cosine_map@50
value: 0.6164549363998423
name: Cosine Map@50
- type: cosine_map@100
value: 0.6177399809348343
name: Cosine Map@100
- type: cosine_map@150
value: 0.6180987489538199
name: Cosine Map@150
- type: cosine_map@200
value: 0.6182392251747794
name: Cosine Map@200
- type: cosine_map@500
value: 0.618438452624424
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix de
type: mix_de
metrics:
- type: cosine_accuracy@1
value: 0.5501820072802912
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.875715028601144
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9334373374934998
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9578783151326054
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.968798751950078
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9771190847633905
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.5501820072802912
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.10808632345293812
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.047665106604264186
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.025169006760270413
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.017205754896862536
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.013109724388975563
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.20695961171780206
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.7888455538221528
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.8676980412549836
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.91352920783498
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.9362367828046455
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.951291384988733
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.5501820072802912
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.6448940133190817
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6665823406307751
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.6769109649623175
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.6813839836815733
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.6841263896292673
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.5501820072802912
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.6404980755674814
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.6424799446207491
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.6428438772177503
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.6429316774029018
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.6429786628088062
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.5501820072802912
name: Cosine Map@1
- type: cosine_map@20
value: 0.5552666840642385
name: Cosine Map@20
- type: cosine_map@50
value: 0.560692088371109
name: Cosine Map@50
- type: cosine_map@100
value: 0.5621625672472186
name: Cosine Map@100
- type: cosine_map@150
value: 0.5625833020357084
name: Cosine Map@150
- type: cosine_map@200
value: 0.56278042754345
name: Cosine Map@200
- type: cosine_map@500
value: 0.5630480560935588
name: Cosine Map@500
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: mix zh
type: mix_zh
metrics:
- type: cosine_accuracy@1
value: 0.5955114822546973
name: Cosine Accuracy@1
- type: cosine_accuracy@20
value: 0.9561586638830898
name: Cosine Accuracy@20
- type: cosine_accuracy@50
value: 0.9786012526096033
name: Cosine Accuracy@50
- type: cosine_accuracy@100
value: 0.9864300626304802
name: Cosine Accuracy@100
- type: cosine_accuracy@150
value: 0.9906054279749478
name: Cosine Accuracy@150
- type: cosine_accuracy@200
value: 0.9932150313152401
name: Cosine Accuracy@200
- type: cosine_precision@1
value: 0.5955114822546973
name: Cosine Precision@1
- type: cosine_precision@20
value: 0.12554801670146137
name: Cosine Precision@20
- type: cosine_precision@50
value: 0.05501043841336119
name: Cosine Precision@50
- type: cosine_precision@100
value: 0.02865866388308978
name: Cosine Precision@100
- type: cosine_precision@150
value: 0.019373695198329852
name: Cosine Precision@150
- type: cosine_precision@200
value: 0.014681628392484347
name: Cosine Precision@200
- type: cosine_recall@1
value: 0.19977010637240283
name: Cosine Recall@1
- type: cosine_recall@20
value: 0.8278618649965205
name: Cosine Recall@20
- type: cosine_recall@50
value: 0.9067762700069589
name: Cosine Recall@50
- type: cosine_recall@100
value: 0.9447807933194153
name: Cosine Recall@100
- type: cosine_recall@150
value: 0.9583072372999304
name: Cosine Recall@150
- type: cosine_recall@200
value: 0.9682846207376479
name: Cosine Recall@200
- type: cosine_ndcg@1
value: 0.5955114822546973
name: Cosine Ndcg@1
- type: cosine_ndcg@20
value: 0.676323551645566
name: Cosine Ndcg@20
- type: cosine_ndcg@50
value: 0.6987334593425172
name: Cosine Ndcg@50
- type: cosine_ndcg@100
value: 0.7074200858340325
name: Cosine Ndcg@100
- type: cosine_ndcg@150
value: 0.7101515061400856
name: Cosine Ndcg@150
- type: cosine_ndcg@200
value: 0.712042637638368
name: Cosine Ndcg@200
- type: cosine_mrr@1
value: 0.5955114822546973
name: Cosine Mrr@1
- type: cosine_mrr@20
value: 0.7139042324770738
name: Cosine Mrr@20
- type: cosine_mrr@50
value: 0.7146770598021757
name: Cosine Mrr@50
- type: cosine_mrr@100
value: 0.7147894374036499
name: Cosine Mrr@100
- type: cosine_mrr@150
value: 0.7148235404346408
name: Cosine Mrr@150
- type: cosine_mrr@200
value: 0.714837920986055
name: Cosine Mrr@200
- type: cosine_map@1
value: 0.5955114822546973
name: Cosine Map@1
- type: cosine_map@20
value: 0.5551824910488451
name: Cosine Map@20
- type: cosine_map@50
value: 0.5618046889714401
name: Cosine Map@50
- type: cosine_map@100
value: 0.5632163208810934
name: Cosine Map@100
- type: cosine_map@150
value: 0.5635017815259477
name: Cosine Map@150
- type: cosine_map@200
value: 0.5636518859615672
name: Cosine Map@200
- type: cosine_map@500
value: 0.5638143166312575
name: Cosine Map@500
SentenceTransformer
This is a sentence-transformers 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
- 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 = [
'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_deandmix_zh - Evaluated with
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 | 0.6602 | 0.624 | 0.5502 | 0.5955 |
| cosine_accuracy@20 | 0.9714 | 1.0 | 0.9704 | 0.9709 | 0.9085 | 0.8757 | 0.9562 |
| cosine_accuracy@50 | 0.9905 | 1.0 | 0.9754 | 0.9903 | 0.9449 | 0.9334 | 0.9786 |
| cosine_accuracy@100 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9709 | 0.9579 | 0.9864 |
| cosine_accuracy@150 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9813 | 0.9688 | 0.9906 |
| cosine_accuracy@200 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9891 | 0.9771 | 0.9932 |
| cosine_precision@1 | 0.6286 | 0.1135 | 0.2956 | 0.6602 | 0.624 | 0.5502 | 0.5955 |
| cosine_precision@20 | 0.4724 | 0.5251 | 0.4224 | 0.4447 | 0.1108 | 0.1081 | 0.1255 |
| cosine_precision@50 | 0.2851 | 0.3408 | 0.2934 | 0.2701 | 0.0482 | 0.0477 | 0.055 |
| cosine_precision@100 | 0.1714 | 0.2172 | 0.1916 | 0.1661 | 0.0252 | 0.0252 | 0.0287 |
| cosine_precision@150 | 0.1236 | 0.1634 | 0.1464 | 0.1199 | 0.0172 | 0.0172 | 0.0194 |
| cosine_precision@200 | 0.0974 | 0.1321 | 0.118 | 0.0951 | 0.013 | 0.0131 | 0.0147 |
| cosine_recall@1 | 0.0657 | 0.0035 | 0.0111 | 0.0661 | 0.2409 | 0.207 | 0.1998 |
| cosine_recall@20 | 0.5028 | 0.3545 | 0.2614 | 0.4824 | 0.823 | 0.7888 | 0.8279 |
| cosine_recall@50 | 0.6769 | 0.5069 | 0.403 | 0.6545 | 0.8928 | 0.8677 | 0.9068 |
| cosine_recall@100 | 0.7838 | 0.6026 | 0.5037 | 0.7666 | 0.9353 | 0.9135 | 0.9448 |
| cosine_recall@150 | 0.837 | 0.6643 | 0.5665 | 0.8214 | 0.9548 | 0.9362 | 0.9583 |
| cosine_recall@200 | 0.8683 | 0.7089 | 0.6046 | 0.8608 | 0.9665 | 0.9513 | 0.9683 |
| cosine_ndcg@1 | 0.6286 | 0.1135 | 0.2956 | 0.6602 | 0.624 | 0.5502 | 0.5955 |
| cosine_ndcg@20 | 0.6393 | 0.569 | 0.4643 | 0.62 | 0.6941 | 0.6449 | 0.6763 |
| cosine_ndcg@50 | 0.6527 | 0.5323 | 0.4395 | 0.6357 | 0.7132 | 0.6666 | 0.6987 |
| cosine_ndcg@100 | 0.7044 | 0.5554 | 0.4621 | 0.6892 | 0.7225 | 0.6769 | 0.7074 |
| cosine_ndcg@150 | 0.7269 | 0.5851 | 0.4931 | 0.7121 | 0.7264 | 0.6814 | 0.7102 |
| cosine_ndcg@200 | 0.7402 | 0.6059 | 0.5109 | 0.7279 | 0.7285 | 0.6841 | 0.712 |
| cosine_mrr@1 | 0.6286 | 0.1135 | 0.2956 | 0.6602 | 0.624 | 0.5502 | 0.5955 |
| cosine_mrr@20 | 0.7822 | 0.5505 | 0.5051 | 0.8027 | 0.6981 | 0.6405 | 0.7139 |
| cosine_mrr@50 | 0.783 | 0.5505 | 0.5053 | 0.8031 | 0.6993 | 0.6425 | 0.7147 |
| cosine_mrr@100 | 0.783 | 0.5505 | 0.5054 | 0.8031 | 0.6997 | 0.6428 | 0.7148 |
| cosine_mrr@150 | 0.783 | 0.5505 | 0.5054 | 0.8031 | 0.6998 | 0.6429 | 0.7148 |
| cosine_mrr@200 | 0.783 | 0.5505 | 0.5054 | 0.8031 | 0.6999 | 0.643 | 0.7148 |
| cosine_map@1 | 0.6286 | 0.1135 | 0.2956 | 0.6602 | 0.624 | 0.5502 | 0.5955 |
| cosine_map@20 | 0.4954 | 0.4359 | 0.3324 | 0.4706 | 0.6113 | 0.5553 | 0.5552 |
| cosine_map@50 | 0.4781 | 0.3706 | 0.2811 | 0.454 | 0.6165 | 0.5607 | 0.5618 |
| cosine_map@100 | 0.5059 | 0.3732 | 0.2779 | 0.4805 | 0.6177 | 0.5622 | 0.5632 |
| cosine_map@150 | 0.5144 | 0.3852 | 0.289 | 0.4886 | 0.6181 | 0.5626 | 0.5635 |
| cosine_map@200 | 0.5186 | 0.3921 | 0.2945 | 0.4932 | 0.6182 | 0.5628 | 0.5637 |
| cosine_map@500 | 0.5245 | 0.4025 | 0.3066 | 0.4992 | 0.6184 | 0.563 | 0.5638 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 86,648 training samples
- Columns:
sentenceandlabel - Approximate statistics based on the first 1000 samples:
sentence label type string list details - min: 2 tokens
- mean: 8.25 tokens
- max: 54 tokens
- size: 768 elements
- 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
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsper_device_train_batch_size: 128per_device_eval_batch_size: 128gradient_accumulation_steps: 2learning_rate: 0.0001num_train_epochs: 5warmup_ratio: 0.05log_on_each_node: Falsefp16: Truedataloader_num_workers: 4ddp_find_unused_parameters: Truebatch_sampler: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 128per_device_eval_batch_size: 128per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 2eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 0.0001weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 5max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.05warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Falselogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Truedataloader_num_workers: 4dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}tp_size: 0fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Trueddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: Nonebatch_sampler: no_duplicatesmulti_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 |
| 3.2544 | 1100 | 0.0003 | - | - | - | - | - | - | - |
| 3.5503 | 1200 | 0.0003 | 0.7402 | 0.6059 | 0.5109 | 0.7279 | 0.7285 | 0.6841 | 0.7120 |
Framework Versions
- Python: 3.11.11
- Sentence Transformers: 4.1.0
- Transformers: 4.51.3
- PyTorch: 2.6.0+cu124
- Accelerate: 1.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
MSELoss
@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",
}