|
--- |
|
language: [] |
|
library_name: sentence-transformers |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
- dataset_size:100K<n<1M |
|
- loss:AnglELoss |
|
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2 |
|
metrics: |
|
- pearson_cosine |
|
- spearman_cosine |
|
- pearson_manhattan |
|
- spearman_manhattan |
|
- pearson_euclidean |
|
- spearman_euclidean |
|
- pearson_dot |
|
- spearman_dot |
|
- pearson_max |
|
- spearman_max |
|
widget: |
|
- source_sentence: 有些人在路上溜达。 |
|
sentences: |
|
- Folk går |
|
- Otururken gitar çalan adam. |
|
- ארה"ב קבעה שסוריה השתמשה בנשק כימי |
|
- source_sentence: 緬甸以前稱為緬甸。 |
|
sentences: |
|
- 缅甸以前叫缅甸。 |
|
- This is very contradictory. |
|
- 한 남자가 아기를 안고 의자에 앉아 잠들어 있다. |
|
- source_sentence: אדם כותב. |
|
sentences: |
|
- האדם כותב. |
|
- questa non è una risposta. |
|
- 7 שוטרים נהרגו ו-4 שוטרים נפצעו. |
|
- source_sentence: הם מפחדים. |
|
sentences: |
|
- liên quan đến rủi ro đáng kể; |
|
- A man is playing a guitar. |
|
- A man is playing a piano. |
|
- source_sentence: 一个女人正在洗澡。 |
|
sentences: |
|
- A woman is taking a bath. |
|
- En jente børster håret sitt |
|
- אדם מחלק תפוח אדמה. |
|
pipeline_tag: sentence-similarity |
|
model-index: |
|
- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2 |
|
results: |
|
- task: |
|
type: semantic-similarity |
|
name: Semantic Similarity |
|
dataset: |
|
name: sts dev |
|
type: sts-dev |
|
metrics: |
|
- type: pearson_cosine |
|
value: 0.9551466915019567 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9592676437617756 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.9270103565661432 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.9382925369644322 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.9278315400036575 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.9393641949848517 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8760113280718741 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8864509380027734 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9551466915019567 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9592676437617756 |
|
name: Spearman Max |
|
- task: |
|
type: semantic-similarity |
|
name: Semantic Similarity |
|
dataset: |
|
name: sts test |
|
type: sts-test |
|
metrics: |
|
- type: pearson_cosine |
|
value: 0.9479585032380113 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9514910354916427 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.925192141913064 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.9351648026362221 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.9258239806908134 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.9363652577900217 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8442947652156254 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8435104766124126 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9479585032380113 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9514910354916427 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9725274765440489 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9766335692570665 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.9382317294386867 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.948654920505423 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.9392057529290415 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.9500099103637895 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8531236460319379 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8611492409185547 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9725274765440489 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9766335692570665 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.8026922386812214 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.8124393788492182 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.7839394479918361 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7899571854314883 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.7835912695413444 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.7920219916708612 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.7698701769634279 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.781996122357711 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.8026922386812214 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.8124393788492182 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.7795928581740468 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.7703365842088069 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.7903764226370217 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7829879213871844 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.7911863454505806 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.7841695636601043 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.7077312955932407 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.6914225616023565 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.7911863454505806 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.7841695636601043 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9112700251605085 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9109414091487618 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8969826303560867 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.8934356058163047 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8986106629139636 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8954517657266873 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.884386067267308 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8922685778872441 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9112700251605085 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9109414091487618 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9361870787330656 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9378741534997558 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.9230051982649123 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.9244721677465636 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.9230904520135751 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.9251248730902872 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.9069963151228692 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.9185797530151516 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9361870787330656 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9378741534997558 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.8048757108412675 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.7987027653005363 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8017660413612523 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7828168153285264 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8006665075585622 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.7824761741785664 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.7894710045147775 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.7819409907917216 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.8048757108412675 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.7987027653005363 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.8520160385093393 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.8553203530552356 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8464006282913296 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.8409514527398295 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8467543977447098 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8458591066828018 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8093136598158064 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8153571493902085 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.8520160385093393 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.8553203530552356 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.8751983236341568 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.872701191632785 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8744834146908832 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.8661385734785878 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.874802989814616 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8668384026485944 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8603441420083793 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8519571499551175 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.8751983236341568 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.872701191632785 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9082404991830442 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9067607122592818 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8908378724095692 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.885184918244054 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8907567800603056 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8850799779856109 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8888621290344544 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8965880419316619 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9082404991830442 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9067607122592818 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9249796814520836 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9246785886944904 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.9083667986520362 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.90288714821411 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.9115880396459031 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.9083794061358542 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.9000889923763985 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.9070443969139744 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9249796814520836 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9246785886944904 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.9133091498737149 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.9114826394926738 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8977113793113364 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.8933433506440468 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8979058595014344 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8937323599537337 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.891219202934611 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8987764114969254 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.9133091498737149 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.9114826394926738 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.8984578585216539 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.8451542547285167 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.8714879175346363 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.8451542547285167 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.8809190484217423 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.8451542547285167 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.8537957222589418 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.8451542547285167 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.8984578585216539 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.8451542547285167 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6494815112978085 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6385354535483773 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.6429493098908716 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6473666993823523 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.6442945700268683 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6444758519763731 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.6128358976757747 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.6108258021881942 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6494815112978085 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6473666993823523 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.7441341150359049 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.7518021273920814 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.7339108684091178 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7367402927783612 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.7336764576613932 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.734241088471987 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.6886320720189693 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.698561864698337 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.7441341150359049 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.7518021273920814 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6278594754203957 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6319430830291571 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.543548091135791 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6002053211770223 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.5399866615749636 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.5955360076924765 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.5657998544710718 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.6068611192160528 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6278594754203957 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6319430830291571 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.7778538763931996 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.7875616631597785 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.7425757616272681 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7789392103102715 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.7437054735775576 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.780583955651507 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.7214423493083364 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.7489073787091952 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.7778538763931996 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.7875616631597785 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.526790729806662 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.5774252131250034 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.41713442172065224 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.5599676717727231 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.42192411421528214 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.5665444422359257 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.49809047501575476 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5367148143234142 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.526790729806662 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.5774252131250034 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6306061651851392 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6383757017928495 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.603366556372183 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6167955278711116 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.6081018686388112 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6219639110001453 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.5767081284665276 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5831358067917275 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6306061651851392 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6383757017928495 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.5568482062575557 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.5866853707548388 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.49244450938868833 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.5737511662255662 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.49058760093828624 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.5762095703672849 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.4306984514506903 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5470683854030187 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.5568482062575557 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.5866853707548388 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.5776222742798018 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.5749790581441845 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.571787148920759 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.5500811027014174 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.5695499775959532 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.5532223379017994 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.53146407233978 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5190797374963447 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.5776222742798018 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.5749790581441845 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.3571900232473057 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.4335552432730643 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.20808854264339055 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.4354537154533896 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.208616390027902 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.440246452767669 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.22336496195751424 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.3706905558756734 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.3571900232473057 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.440246452767669 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6863427356006826 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6620948502618977 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.6428578762643233 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6483663123081533 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.6424050032110411 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6485902628925195 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.6352371374824808 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.6159110999161411 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6863427356006826 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6620948502618977 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.7570295008280781 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.7510805416538202 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.7191097960855934 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.7140422377894933 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.7204228437397647 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.7257632200250398 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.7144336778935939 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.7284199759984302 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.7570295008280781 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.7510805416538202 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6502825737911098 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6624635951676386 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.647419285100459 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6589805549915764 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.6516956762905051 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6667221229271868 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.5646710115576599 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.570198719868156 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6516956762905051 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6667221229271868 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6774230420538705 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6537294853166558 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.6824702119604247 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6324707043840341 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.6905615468119815 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.640725065351179 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.5834798827905125 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5962447037764929 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6905615468119815 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6537294853166558 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.6709478850576526 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6847049462613332 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.6612883666796053 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6906896123993531 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.66070522554664 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6880796473119815 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.609762034287328 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.6194587632000961 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.6709478850576526 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6906896123993531 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.5977420246846783 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.5798716781400349 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.5974348978243684 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.5952597125560467 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.5949256850264925 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.5935900431326085 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.5042542872226021 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.4968394689744579 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.5977420246846783 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.5952597125560467 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.45623521030042163 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.44220332625465214 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.4154787596532877 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.3836945296053597 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.4111357738180186 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.3821548244303783 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.48625234725541483 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5302744622635869 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.48625234725541483 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.5302744622635869 |
|
name: Spearman Max |
|
- type: pearson_cosine |
|
value: 0.5929570742517215 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.6266361518449931 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.5608268850302591 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.6228972623939251 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.5579847474929831 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.6202030126844109 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.4578333834889949 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.5628471668594075 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.5929570742517215 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.6266361518449931 |
|
name: Spearman Max |
|
--- |
|
|
|
/!\ This model achieves SOTA results in the MTEB STS multilingual Leaderboard (in "other"). Here is the comparison |
|
|
|
State-of-the-art results (Multi) STSb-XLM-RoBERTa-base Paraphrase Multilingual MPNet base v2 |
|
Average 73.17 71.68 **73.89** |
|
STS17 (ar-ar) **81.87** 80.43 81.24 |
|
STS17 (en-ar) **81.22** 76.3 77.03 |
|
STS17 (en-de) 87.3 91.06 **91.09** |
|
STS17 (en-tr) 77.18 **80.74** 79.87 |
|
STS17 (es-en) **88.24** 83.09 85.53 |
|
STS17 (es-es) **88.25** 84.16 87.27 |
|
STS17 (fr-en) 88.06 **91.33** 90.68 |
|
STS17 (it-en) 89.68 **92.87** 92.47 |
|
STS17 (ko-ko) 83.69 **97.67** 97.66 |
|
STS17 (nl-en) 88.25 **92.13** 91.15 |
|
STS22 (ar) 58.67 58.67 **62.66** |
|
STS22 (de) **60.12** 52.17 57.74 |
|
STS22 (de-en) **60.92** 58.5 57.5 |
|
STS22 (de-fr) **67.79** 51.28 57.99 |
|
STS22 (de-pl) **58.69** 44.56 44.22 |
|
STS22 (es) **68.57** 63.68 66.21 |
|
STS22 (es-en) **78.8** 70.65 75.18 |
|
STS22 (es-it) **75.04** 60.88 66.25 |
|
STS22 (fr) **83.75** 76.46 78.76 |
|
STS22 (fr-pl) 84.52 84.52 **84.52** |
|
STS22 (it) **79.28** 66.73 68.47 |
|
STS22 (pl) 42.08 41.18 **43.36** |
|
STS22 (pl-en) **77.5** 64.35 75.11 |
|
STS22 (ru) **61.71** 58.59 58.67 |
|
STS22 (tr) **68.72** 57.52 63.84 |
|
STS22 (zh-en) **71.88** 60.69 65.37 |
|
STSb 89.86 95.05 **95.15** |
|
|
|
# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2 |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2). 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:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 79f2382ceacceacdf38563d7c5d16b9ff8d725d6 --> |
|
- **Maximum Sequence Length:** 128 tokens |
|
- **Output Dimensionality:** 768 tokens |
|
- **Similarity Function:** Cosine Similarity |
|
<!-- - **Training Dataset:** Unknown --> |
|
<!-- - **Language:** Unknown --> |
|
<!-- - **License:** Unknown --> |
|
|
|
### Model Sources |
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
|
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
|
### Full Model Architecture |
|
|
|
``` |
|
SentenceTransformer( |
|
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel |
|
(1): Pooling({'word_embedding_dimension': 768, '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}) |
|
) |
|
``` |
|
|
|
## 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("Gameselo/STS-multilingual-mpnet-base-v2") |
|
# Run inference |
|
sentences = [ |
|
'一个女人正在洗澡。', |
|
'A woman is taking a bath.', |
|
'En jente børster håret sitt', |
|
] |
|
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] |
|
``` |
|
|
|
<!-- |
|
### Direct Usage (Transformers) |
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
</details> |
|
--> |
|
|
|
<!-- |
|
### Downstream Usage (Sentence Transformers) |
|
|
|
You can finetune this model on your own dataset. |
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
</details> |
|
--> |
|
|
|
<!-- |
|
### Out-of-Scope Use |
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
--> |
|
|
|
## Evaluation |
|
|
|
### Metrics |
|
|
|
#### Semantic Similarity |
|
* Dataset: `sts-dev` |
|
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) |
|
|
|
| Metric | Value | |
|
|:--------------------|:-----------| |
|
| pearson_cosine | 0.9551 | |
|
| **spearman_cosine** | **0.9593** | |
|
| pearson_manhattan | 0.927 | |
|
| spearman_manhattan | 0.9383 | |
|
| pearson_euclidean | 0.9278 | |
|
| spearman_euclidean | 0.9394 | |
|
| pearson_dot | 0.876 | |
|
| spearman_dot | 0.8865 | |
|
| pearson_max | 0.9551 | |
|
| spearman_max | 0.9593 | |
|
|
|
#### Evalutation results vs SOTA results |
|
* Dataset: `sts-test` |
|
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) |
|
|
|
| Metric | Value | |
|
|:--------------------|:-----------| |
|
| pearson_cosine | 0.948 | |
|
| **spearman_cosine** | **0.9515** | |
|
| pearson_manhattan | 0.9252 | |
|
| spearman_manhattan | 0.9352 | |
|
| pearson_euclidean | 0.9258 | |
|
| spearman_euclidean | 0.9364 | |
|
| pearson_dot | 0.8443 | |
|
| spearman_dot | 0.8435 | |
|
| pearson_max | 0.948 | |
|
| spearman_max | 0.9515 | |
|
|
|
<!-- |
|
## Bias, Risks and Limitations |
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
--> |
|
|
|
<!-- |
|
### Recommendations |
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
--> |
|
|
|
## Training Details |
|
|
|
### Training Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 226,547 training samples |
|
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | sentence_0 | sentence_1 | label | |
|
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------| |
|
| type | string | string | float | |
|
| details | <ul><li>min: 3 tokens</li><li>mean: 20.05 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.94 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 1.92</li><li>max: 398.6</li></ul> | |
|
* Samples: |
|
| sentence_0 | sentence_1 | label | |
|
|:-------------------------------------------------------------------|:----------------------------------------------------------------|:---------------------------------| |
|
| <code>Bir kadın makineye dikiş dikiyor.</code> | <code>Bir kadın biraz et ekiyor.</code> | <code>0.12</code> | |
|
| <code>Snowden 'gegeven vluchtelingendocument door Ecuador'.</code> | <code>Snowden staat op het punt om uit Moskou te vliegen</code> | <code>0.24000000953674316</code> | |
|
| <code>Czarny pies idzie mostem przez wodę</code> | <code>Czarny pies nie idzie mostem przez wodę</code> | <code>0.74000000954</code> | |
|
* Loss: [<code>AnglELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#angleloss) with these parameters: |
|
```json |
|
{ |
|
"scale": 20.0, |
|
"similarity_fct": "pairwise_angle_sim" |
|
} |
|
``` |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `per_device_train_batch_size`: 256 |
|
- `per_device_eval_batch_size`: 256 |
|
- `num_train_epochs`: 10 |
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
#### All Hyperparameters |
|
<details><summary>Click to expand</summary> |
|
|
|
- `overwrite_output_dir`: False |
|
- `do_predict`: False |
|
- `prediction_loss_only`: True |
|
- `per_device_train_batch_size`: 256 |
|
- `per_device_eval_batch_size`: 256 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 1 |
|
- `eval_accumulation_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 |
|
- `num_train_epochs`: 10 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: linear |
|
- `lr_scheduler_kwargs`: {} |
|
- `warmup_ratio`: 0.0 |
|
- `warmup_steps`: 0 |
|
- `log_level`: passive |
|
- `log_level_replica`: warning |
|
- `log_on_each_node`: True |
|
- `logging_nan_inf_filter`: True |
|
- `save_safetensors`: True |
|
- `save_on_each_node`: False |
|
- `save_only_model`: 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`: False |
|
- `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`: False |
|
- `dataloader_num_workers`: 0 |
|
- `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} |
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, '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`: None |
|
- `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`: False |
|
- `hub_always_push`: False |
|
- `gradient_checkpointing`: False |
|
- `gradient_checkpointing_kwargs`: None |
|
- `include_inputs_for_metrics`: False |
|
- `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 |
|
- `dispatch_batches`: None |
|
- `split_batches`: None |
|
- `include_tokens_per_second`: False |
|
- `include_num_input_tokens_seen`: False |
|
- `neftune_noise_alpha`: None |
|
- `optim_target_modules`: None |
|
- `batch_sampler`: batch_sampler |
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine | |
|
|:------:|:----:|:-------------:|:-----------------------:|:------------------------:| |
|
| 0.5650 | 500 | 10.9426 | - | - | |
|
| 1.0 | 885 | - | 0.9202 | - | |
|
| 1.1299 | 1000 | 9.7184 | - | - | |
|
| 1.6949 | 1500 | 9.5348 | - | - | |
|
| 2.0 | 1770 | - | 0.9400 | - | |
|
| 2.2599 | 2000 | 9.4412 | - | - | |
|
| 2.8249 | 2500 | 9.3097 | - | - | |
|
| 3.0 | 2655 | - | 0.9489 | - | |
|
| 3.3898 | 3000 | 9.2357 | - | - | |
|
| 3.9548 | 3500 | 9.1594 | - | - | |
|
| 4.0 | 3540 | - | 0.9528 | - | |
|
| 4.5198 | 4000 | 9.0963 | - | - | |
|
| 5.0 | 4425 | - | 0.9553 | - | |
|
| 5.0847 | 4500 | 9.0382 | - | - | |
|
| 5.6497 | 5000 | 8.9837 | - | - | |
|
| 6.0 | 5310 | - | 0.9567 | - | |
|
| 6.2147 | 5500 | 8.9403 | - | - | |
|
| 6.7797 | 6000 | 8.8841 | - | - | |
|
| 7.0 | 6195 | - | 0.9581 | - | |
|
| 7.3446 | 6500 | 8.8513 | - | - | |
|
| 7.9096 | 7000 | 8.81 | - | - | |
|
| 8.0 | 7080 | - | 0.9582 | - | |
|
| 8.4746 | 7500 | 8.8069 | - | - | |
|
| 9.0 | 7965 | - | 0.9589 | - | |
|
| 9.0395 | 8000 | 8.7616 | - | - | |
|
| 9.6045 | 8500 | 8.7521 | - | - | |
|
| 10.0 | 8850 | - | 0.9593 | 0.6266 | |
|
|
|
|
|
### Framework Versions |
|
- Python: 3.9.7 |
|
- Sentence Transformers: 3.0.0 |
|
- Transformers: 4.40.1 |
|
- PyTorch: 2.3.0+cu121 |
|
- Accelerate: 0.29.3 |
|
- Datasets: 2.19.0 |
|
- Tokenizers: 0.19.1 |
|
|
|
## 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", |
|
} |
|
``` |
|
|
|
#### AnglELoss |
|
```bibtex |
|
@misc{li2023angleoptimized, |
|
title={AnglE-optimized Text Embeddings}, |
|
author={Xianming Li and Jing Li}, |
|
year={2023}, |
|
eprint={2309.12871}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL} |
|
} |
|
``` |
|
|
|
<!-- |
|
## Glossary |
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Authors |
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
--> |
|
|
|
<!-- |
|
## Model Card Contact |
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
--> |
