|
--- |
|
model-index: |
|
- name: karsar/paraphrase-multilingual-MiniLM-L12-hu_v1 |
|
results: |
|
- dataset: |
|
config: hun_Latn-hun_Latn |
|
name: MTEB BelebeleRetrieval (hun_Latn-hun_Latn) |
|
revision: 75b399394a9803252cfec289d103de462763db7c |
|
split: test |
|
type: facebook/belebele |
|
metrics: |
|
- type: main_score |
|
value: 77.865 |
|
- type: map_at_1 |
|
value: 67.333 |
|
- type: map_at_10 |
|
value: 74.404 |
|
- type: map_at_100 |
|
value: 74.802 |
|
- type: map_at_1000 |
|
value: 74.809 |
|
- type: map_at_20 |
|
value: 74.63 |
|
- type: map_at_3 |
|
value: 72.796 |
|
- type: map_at_5 |
|
value: 73.67399999999999 |
|
- type: mrr_at_1 |
|
value: 67.33333333333333 |
|
- type: mrr_at_10 |
|
value: 74.40396825396829 |
|
- type: mrr_at_100 |
|
value: 74.80177264047548 |
|
- type: mrr_at_1000 |
|
value: 74.80937346439818 |
|
- type: mrr_at_20 |
|
value: 74.62979204843244 |
|
- type: mrr_at_3 |
|
value: 72.7962962962963 |
|
- type: mrr_at_5 |
|
value: 73.6740740740741 |
|
- type: nauc_map_at_1000_diff1 |
|
value: 76.08133094195743 |
|
- type: nauc_map_at_1000_max |
|
value: 61.727834175182736 |
|
- type: nauc_map_at_1000_std |
|
value: -2.3231732437794568 |
|
- type: nauc_map_at_100_diff1 |
|
value: 76.07916259051902 |
|
- type: nauc_map_at_100_max |
|
value: 61.72703450852774 |
|
- type: nauc_map_at_100_std |
|
value: -2.3175338063349575 |
|
- type: nauc_map_at_10_diff1 |
|
value: 75.97996147738112 |
|
- type: nauc_map_at_10_max |
|
value: 61.860784493617224 |
|
- type: nauc_map_at_10_std |
|
value: -2.4887315051072356 |
|
- type: nauc_map_at_1_diff1 |
|
value: 78.13561632940586 |
|
- type: nauc_map_at_1_max |
|
value: 59.243520843511746 |
|
- type: nauc_map_at_1_std |
|
value: -2.6689239089679515 |
|
- type: nauc_map_at_20_diff1 |
|
value: 76.06883452011327 |
|
- type: nauc_map_at_20_max |
|
value: 61.775589074510826 |
|
- type: nauc_map_at_20_std |
|
value: -2.3905575770447585 |
|
- type: nauc_map_at_3_diff1 |
|
value: 75.85937006372846 |
|
- type: nauc_map_at_3_max |
|
value: 61.819093557650895 |
|
- type: nauc_map_at_3_std |
|
value: -2.5207238945764647 |
|
- type: nauc_map_at_5_diff1 |
|
value: 76.06929563357589 |
|
- type: nauc_map_at_5_max |
|
value: 61.93563829360039 |
|
- type: nauc_map_at_5_std |
|
value: -1.9424637593671918 |
|
- type: nauc_mrr_at_1000_diff1 |
|
value: 76.08133094195743 |
|
- type: nauc_mrr_at_1000_max |
|
value: 61.727834175182736 |
|
- type: nauc_mrr_at_1000_std |
|
value: -2.3231732437794568 |
|
- type: nauc_mrr_at_100_diff1 |
|
value: 76.07916259051902 |
|
- type: nauc_mrr_at_100_max |
|
value: 61.72703450852774 |
|
- type: nauc_mrr_at_100_std |
|
value: -2.3175338063349575 |
|
- type: nauc_mrr_at_10_diff1 |
|
value: 75.97996147738112 |
|
- type: nauc_mrr_at_10_max |
|
value: 61.860784493617224 |
|
- type: nauc_mrr_at_10_std |
|
value: -2.4887315051072356 |
|
- type: nauc_mrr_at_1_diff1 |
|
value: 78.13561632940586 |
|
- type: nauc_mrr_at_1_max |
|
value: 59.243520843511746 |
|
- type: nauc_mrr_at_1_std |
|
value: -2.6689239089679515 |
|
- type: nauc_mrr_at_20_diff1 |
|
value: 76.06883452011327 |
|
- type: nauc_mrr_at_20_max |
|
value: 61.775589074510826 |
|
- type: nauc_mrr_at_20_std |
|
value: -2.3905575770447585 |
|
- type: nauc_mrr_at_3_diff1 |
|
value: 75.85937006372846 |
|
- type: nauc_mrr_at_3_max |
|
value: 61.819093557650895 |
|
- type: nauc_mrr_at_3_std |
|
value: -2.5207238945764647 |
|
- type: nauc_mrr_at_5_diff1 |
|
value: 76.06929563357589 |
|
- type: nauc_mrr_at_5_max |
|
value: 61.93563829360039 |
|
- type: nauc_mrr_at_5_std |
|
value: -1.9424637593671918 |
|
- type: nauc_ndcg_at_1000_diff1 |
|
value: 75.7057240434196 |
|
- type: nauc_ndcg_at_1000_max |
|
value: 62.021717989510385 |
|
- type: nauc_ndcg_at_1000_std |
|
value: -2.2522490330905103 |
|
- type: nauc_ndcg_at_100_diff1 |
|
value: 75.62156032414751 |
|
- type: nauc_ndcg_at_100_max |
|
value: 61.97932968109654 |
|
- type: nauc_ndcg_at_100_std |
|
value: -2.0118635701265375 |
|
- type: nauc_ndcg_at_10_diff1 |
|
value: 75.09836101324169 |
|
- type: nauc_ndcg_at_10_max |
|
value: 62.703427209156736 |
|
- type: nauc_ndcg_at_10_std |
|
value: -2.9287738405282395 |
|
- type: nauc_ndcg_at_1_diff1 |
|
value: 78.13561632940586 |
|
- type: nauc_ndcg_at_1_max |
|
value: 59.243520843511746 |
|
- type: nauc_ndcg_at_1_std |
|
value: -2.6689239089679515 |
|
- type: nauc_ndcg_at_20_diff1 |
|
value: 75.46348763248093 |
|
- type: nauc_ndcg_at_20_max |
|
value: 62.35498579351012 |
|
- type: nauc_ndcg_at_20_std |
|
value: -2.577338920595739 |
|
- type: nauc_ndcg_at_3_diff1 |
|
value: 74.92773626606146 |
|
- type: nauc_ndcg_at_3_max |
|
value: 62.55812080913172 |
|
- type: nauc_ndcg_at_3_std |
|
value: -2.5630879822636476 |
|
- type: nauc_ndcg_at_5_diff1 |
|
value: 75.3100398038724 |
|
- type: nauc_ndcg_at_5_max |
|
value: 62.81733471459409 |
|
- type: nauc_ndcg_at_5_std |
|
value: -1.501748019065971 |
|
- type: nauc_precision_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_precision_at_1000_max |
|
value: .nan |
|
- type: nauc_precision_at_1000_std |
|
value: .nan |
|
- type: nauc_precision_at_100_diff1 |
|
value: 66.63165266106552 |
|
- type: nauc_precision_at_100_max |
|
value: 57.60582010582053 |
|
- type: nauc_precision_at_100_std |
|
value: 23.844537815126937 |
|
- type: nauc_precision_at_10_diff1 |
|
value: 70.08984254109942 |
|
- type: nauc_precision_at_10_max |
|
value: 67.45880653843606 |
|
- type: nauc_precision_at_10_std |
|
value: -6.3555626412584 |
|
- type: nauc_precision_at_1_diff1 |
|
value: 78.13561632940586 |
|
- type: nauc_precision_at_1_max |
|
value: 59.243520843511746 |
|
- type: nauc_precision_at_1_std |
|
value: -2.6689239089679515 |
|
- type: nauc_precision_at_20_diff1 |
|
value: 71.63306637208878 |
|
- type: nauc_precision_at_20_max |
|
value: 65.99137307505141 |
|
- type: nauc_precision_at_20_std |
|
value: -4.675767020423249 |
|
- type: nauc_precision_at_3_diff1 |
|
value: 71.57608769475272 |
|
- type: nauc_precision_at_3_max |
|
value: 65.10683383365713 |
|
- type: nauc_precision_at_3_std |
|
value: -2.7514636167292985 |
|
- type: nauc_precision_at_5_diff1 |
|
value: 72.21412151067312 |
|
- type: nauc_precision_at_5_max |
|
value: 66.43448275862069 |
|
- type: nauc_precision_at_5_std |
|
value: 0.4555008210180189 |
|
- type: nauc_recall_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_recall_at_1000_max |
|
value: .nan |
|
- type: nauc_recall_at_1000_std |
|
value: .nan |
|
- type: nauc_recall_at_100_diff1 |
|
value: 66.63165266106327 |
|
- type: nauc_recall_at_100_max |
|
value: 57.60582010581922 |
|
- type: nauc_recall_at_100_std |
|
value: 23.844537815125907 |
|
- type: nauc_recall_at_10_diff1 |
|
value: 70.08984254109967 |
|
- type: nauc_recall_at_10_max |
|
value: 67.45880653843632 |
|
- type: nauc_recall_at_10_std |
|
value: -6.355562641258283 |
|
- type: nauc_recall_at_1_diff1 |
|
value: 78.13561632940586 |
|
- type: nauc_recall_at_1_max |
|
value: 59.243520843511746 |
|
- type: nauc_recall_at_1_std |
|
value: -2.6689239089679515 |
|
- type: nauc_recall_at_20_diff1 |
|
value: 71.6330663720887 |
|
- type: nauc_recall_at_20_max |
|
value: 65.9913730750516 |
|
- type: nauc_recall_at_20_std |
|
value: -4.675767020422999 |
|
- type: nauc_recall_at_3_diff1 |
|
value: 71.57608769475274 |
|
- type: nauc_recall_at_3_max |
|
value: 65.106833833657 |
|
- type: nauc_recall_at_3_std |
|
value: -2.7514636167294 |
|
- type: nauc_recall_at_5_diff1 |
|
value: 72.21412151067315 |
|
- type: nauc_recall_at_5_max |
|
value: 66.43448275862077 |
|
- type: nauc_recall_at_5_std |
|
value: 0.4555008210180812 |
|
- type: ndcg_at_1 |
|
value: 67.333 |
|
- type: ndcg_at_10 |
|
value: 77.865 |
|
- type: ndcg_at_100 |
|
value: 79.927 |
|
- type: ndcg_at_1000 |
|
value: 80.104 |
|
- type: ndcg_at_20 |
|
value: 78.701 |
|
- type: ndcg_at_3 |
|
value: 74.509 |
|
- type: ndcg_at_5 |
|
value: 76.101 |
|
- type: precision_at_1 |
|
value: 67.333 |
|
- type: precision_at_10 |
|
value: 8.878 |
|
- type: precision_at_100 |
|
value: 0.987 |
|
- type: precision_at_1000 |
|
value: 0.1 |
|
- type: precision_at_20 |
|
value: 4.606 |
|
- type: precision_at_3 |
|
value: 26.480999999999998 |
|
- type: precision_at_5 |
|
value: 16.667 |
|
- type: recall_at_1 |
|
value: 67.333 |
|
- type: recall_at_10 |
|
value: 88.778 |
|
- type: recall_at_100 |
|
value: 98.667 |
|
- type: recall_at_1000 |
|
value: 100.0 |
|
- type: recall_at_20 |
|
value: 92.111 |
|
- type: recall_at_3 |
|
value: 79.444 |
|
- type: recall_at_5 |
|
value: 83.333 |
|
task: |
|
type: Retrieval |
|
- dataset: |
|
config: hun_Latn-eng_Latn |
|
name: MTEB BelebeleRetrieval (hun_Latn-eng_Latn) |
|
revision: 75b399394a9803252cfec289d103de462763db7c |
|
split: test |
|
type: facebook/belebele |
|
metrics: |
|
- type: main_score |
|
value: 71.307 |
|
- type: map_at_1 |
|
value: 57.778 |
|
- type: map_at_10 |
|
value: 66.843 |
|
- type: map_at_100 |
|
value: 67.368 |
|
- type: map_at_1000 |
|
value: 67.38300000000001 |
|
- type: map_at_20 |
|
value: 67.162 |
|
- type: map_at_3 |
|
value: 64.704 |
|
- type: map_at_5 |
|
value: 65.97 |
|
- type: mrr_at_1 |
|
value: 57.77777777777777 |
|
- type: mrr_at_10 |
|
value: 66.8428130511464 |
|
- type: mrr_at_100 |
|
value: 67.36803803097415 |
|
- type: mrr_at_1000 |
|
value: 67.38317813286176 |
|
- type: mrr_at_20 |
|
value: 67.16164827986293 |
|
- type: mrr_at_3 |
|
value: 64.7037037037037 |
|
- type: mrr_at_5 |
|
value: 65.97037037037038 |
|
- type: nauc_map_at_1000_diff1 |
|
value: 69.02219987684592 |
|
- type: nauc_map_at_1000_max |
|
value: 60.114123597785785 |
|
- type: nauc_map_at_1000_std |
|
value: 4.880216382742553 |
|
- type: nauc_map_at_100_diff1 |
|
value: 69.01116363727591 |
|
- type: nauc_map_at_100_max |
|
value: 60.11716622079215 |
|
- type: nauc_map_at_100_std |
|
value: 4.890393343425179 |
|
- type: nauc_map_at_10_diff1 |
|
value: 68.95240309900163 |
|
- type: nauc_map_at_10_max |
|
value: 60.124170478386105 |
|
- type: nauc_map_at_10_std |
|
value: 4.819161459028938 |
|
- type: nauc_map_at_1_diff1 |
|
value: 72.45335820895522 |
|
- type: nauc_map_at_1_max |
|
value: 59.127316006176 |
|
- type: nauc_map_at_1_std |
|
value: 6.580191713844538 |
|
- type: nauc_map_at_20_diff1 |
|
value: 68.87249492072671 |
|
- type: nauc_map_at_20_max |
|
value: 60.04834608184139 |
|
- type: nauc_map_at_20_std |
|
value: 4.807958211395879 |
|
- type: nauc_map_at_3_diff1 |
|
value: 69.38092756897547 |
|
- type: nauc_map_at_3_max |
|
value: 60.30271451423346 |
|
- type: nauc_map_at_3_std |
|
value: 3.9374045068220322 |
|
- type: nauc_map_at_5_diff1 |
|
value: 69.10875854889262 |
|
- type: nauc_map_at_5_max |
|
value: 60.24557626138646 |
|
- type: nauc_map_at_5_std |
|
value: 4.271289591515184 |
|
- type: nauc_mrr_at_1000_diff1 |
|
value: 69.02219987684592 |
|
- type: nauc_mrr_at_1000_max |
|
value: 60.114123597785785 |
|
- type: nauc_mrr_at_1000_std |
|
value: 4.880216382742553 |
|
- type: nauc_mrr_at_100_diff1 |
|
value: 69.01116363727591 |
|
- type: nauc_mrr_at_100_max |
|
value: 60.11716622079215 |
|
- type: nauc_mrr_at_100_std |
|
value: 4.890393343425179 |
|
- type: nauc_mrr_at_10_diff1 |
|
value: 68.95240309900163 |
|
- type: nauc_mrr_at_10_max |
|
value: 60.124170478386105 |
|
- type: nauc_mrr_at_10_std |
|
value: 4.819161459028938 |
|
- type: nauc_mrr_at_1_diff1 |
|
value: 72.45335820895522 |
|
- type: nauc_mrr_at_1_max |
|
value: 59.127316006176 |
|
- type: nauc_mrr_at_1_std |
|
value: 6.580191713844538 |
|
- type: nauc_mrr_at_20_diff1 |
|
value: 68.87249492072671 |
|
- type: nauc_mrr_at_20_max |
|
value: 60.04834608184139 |
|
- type: nauc_mrr_at_20_std |
|
value: 4.807958211395879 |
|
- type: nauc_mrr_at_3_diff1 |
|
value: 69.38092756897547 |
|
- type: nauc_mrr_at_3_max |
|
value: 60.30271451423346 |
|
- type: nauc_mrr_at_3_std |
|
value: 3.9374045068220322 |
|
- type: nauc_mrr_at_5_diff1 |
|
value: 69.10875854889262 |
|
- type: nauc_mrr_at_5_max |
|
value: 60.24557626138646 |
|
- type: nauc_mrr_at_5_std |
|
value: 4.271289591515184 |
|
- type: nauc_ndcg_at_1000_diff1 |
|
value: 68.36151731152576 |
|
- type: nauc_ndcg_at_1000_max |
|
value: 60.21499073164881 |
|
- type: nauc_ndcg_at_1000_std |
|
value: 5.019374170320369 |
|
- type: nauc_ndcg_at_100_diff1 |
|
value: 68.12777182930174 |
|
- type: nauc_ndcg_at_100_max |
|
value: 60.293069076013296 |
|
- type: nauc_ndcg_at_100_std |
|
value: 5.375522795479381 |
|
- type: nauc_ndcg_at_10_diff1 |
|
value: 67.46914440211127 |
|
- type: nauc_ndcg_at_10_max |
|
value: 60.210209508170976 |
|
- type: nauc_ndcg_at_10_std |
|
value: 4.921793458534013 |
|
- type: nauc_ndcg_at_1_diff1 |
|
value: 72.45335820895522 |
|
- type: nauc_ndcg_at_1_max |
|
value: 59.127316006176 |
|
- type: nauc_ndcg_at_1_std |
|
value: 6.580191713844538 |
|
- type: nauc_ndcg_at_20_diff1 |
|
value: 67.09692054164125 |
|
- type: nauc_ndcg_at_20_max |
|
value: 59.89689460185056 |
|
- type: nauc_ndcg_at_20_std |
|
value: 4.977631579372532 |
|
- type: nauc_ndcg_at_3_diff1 |
|
value: 68.54468748113734 |
|
- type: nauc_ndcg_at_3_max |
|
value: 60.66886257099051 |
|
- type: nauc_ndcg_at_3_std |
|
value: 3.073807310026356 |
|
- type: nauc_ndcg_at_5_diff1 |
|
value: 67.94441056262235 |
|
- type: nauc_ndcg_at_5_max |
|
value: 60.47774252804478 |
|
- type: nauc_ndcg_at_5_std |
|
value: 3.572034464519458 |
|
- type: nauc_precision_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_precision_at_1000_max |
|
value: .nan |
|
- type: nauc_precision_at_1000_std |
|
value: .nan |
|
- type: nauc_precision_at_100_diff1 |
|
value: 52.808123249299676 |
|
- type: nauc_precision_at_100_max |
|
value: 65.81699346405254 |
|
- type: nauc_precision_at_100_std |
|
value: 31.809056956116383 |
|
- type: nauc_precision_at_10_diff1 |
|
value: 59.02820830750145 |
|
- type: nauc_precision_at_10_max |
|
value: 60.33787972721626 |
|
- type: nauc_precision_at_10_std |
|
value: 6.405175213296739 |
|
- type: nauc_precision_at_1_diff1 |
|
value: 72.45335820895522 |
|
- type: nauc_precision_at_1_max |
|
value: 59.127316006176 |
|
- type: nauc_precision_at_1_std |
|
value: 6.580191713844538 |
|
- type: nauc_precision_at_20_diff1 |
|
value: 52.242994576107485 |
|
- type: nauc_precision_at_20_max |
|
value: 57.56617253643015 |
|
- type: nauc_precision_at_20_std |
|
value: 7.9884388212213455 |
|
- type: nauc_precision_at_3_diff1 |
|
value: 65.73191064426206 |
|
- type: nauc_precision_at_3_max |
|
value: 61.92373010829596 |
|
- type: nauc_precision_at_3_std |
|
value: 0.096317142458587 |
|
- type: nauc_precision_at_5_diff1 |
|
value: 63.20464039592358 |
|
- type: nauc_precision_at_5_max |
|
value: 61.25721735891223 |
|
- type: nauc_precision_at_5_std |
|
value: 0.7937099220392029 |
|
- type: nauc_recall_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_recall_at_1000_max |
|
value: .nan |
|
- type: nauc_recall_at_1000_std |
|
value: .nan |
|
- type: nauc_recall_at_100_diff1 |
|
value: 52.80812324929921 |
|
- type: nauc_recall_at_100_max |
|
value: 65.81699346405242 |
|
- type: nauc_recall_at_100_std |
|
value: 31.809056956115235 |
|
- type: nauc_recall_at_10_diff1 |
|
value: 59.02820830750159 |
|
- type: nauc_recall_at_10_max |
|
value: 60.337879727216446 |
|
- type: nauc_recall_at_10_std |
|
value: 6.405175213296646 |
|
- type: nauc_recall_at_1_diff1 |
|
value: 72.45335820895522 |
|
- type: nauc_recall_at_1_max |
|
value: 59.127316006176 |
|
- type: nauc_recall_at_1_std |
|
value: 6.580191713844538 |
|
- type: nauc_recall_at_20_diff1 |
|
value: 52.242994576107534 |
|
- type: nauc_recall_at_20_max |
|
value: 57.56617253643034 |
|
- type: nauc_recall_at_20_std |
|
value: 7.988438821221468 |
|
- type: nauc_recall_at_3_diff1 |
|
value: 65.73191064426209 |
|
- type: nauc_recall_at_3_max |
|
value: 61.923730108295906 |
|
- type: nauc_recall_at_3_std |
|
value: 0.09631714245861488 |
|
- type: nauc_recall_at_5_diff1 |
|
value: 63.204640395923626 |
|
- type: nauc_recall_at_5_max |
|
value: 61.25721735891235 |
|
- type: nauc_recall_at_5_std |
|
value: 0.7937099220392697 |
|
- type: ndcg_at_1 |
|
value: 57.778 |
|
- type: ndcg_at_10 |
|
value: 71.307 |
|
- type: ndcg_at_100 |
|
value: 73.942 |
|
- type: ndcg_at_1000 |
|
value: 74.248 |
|
- type: ndcg_at_20 |
|
value: 72.499 |
|
- type: ndcg_at_3 |
|
value: 66.95 |
|
- type: ndcg_at_5 |
|
value: 69.21199999999999 |
|
- type: precision_at_1 |
|
value: 57.778 |
|
- type: precision_at_10 |
|
value: 8.533 |
|
- type: precision_at_100 |
|
value: 0.9780000000000001 |
|
- type: precision_at_1000 |
|
value: 0.1 |
|
- type: precision_at_20 |
|
value: 4.506 |
|
- type: precision_at_3 |
|
value: 24.481 |
|
- type: precision_at_5 |
|
value: 15.778 |
|
- type: recall_at_1 |
|
value: 57.778 |
|
- type: recall_at_10 |
|
value: 85.333 |
|
- type: recall_at_100 |
|
value: 97.77799999999999 |
|
- type: recall_at_1000 |
|
value: 100.0 |
|
- type: recall_at_20 |
|
value: 90.11099999999999 |
|
- type: recall_at_3 |
|
value: 73.444 |
|
- type: recall_at_5 |
|
value: 78.889 |
|
task: |
|
type: Retrieval |
|
- dataset: |
|
config: eng_Latn-hun_Latn |
|
name: MTEB BelebeleRetrieval (eng_Latn-hun_Latn) |
|
revision: 75b399394a9803252cfec289d103de462763db7c |
|
split: test |
|
type: facebook/belebele |
|
metrics: |
|
- type: main_score |
|
value: 73.668 |
|
- type: map_at_1 |
|
value: 60.778 |
|
- type: map_at_10 |
|
value: 69.571 |
|
- type: map_at_100 |
|
value: 70.114 |
|
- type: map_at_1000 |
|
value: 70.124 |
|
- type: map_at_20 |
|
value: 69.93700000000001 |
|
- type: map_at_3 |
|
value: 67.778 |
|
- type: map_at_5 |
|
value: 68.872 |
|
- type: mrr_at_1 |
|
value: 60.77777777777777 |
|
- type: mrr_at_10 |
|
value: 69.57142857142857 |
|
- type: mrr_at_100 |
|
value: 70.1136336675579 |
|
- type: mrr_at_1000 |
|
value: 70.12432347462514 |
|
- type: mrr_at_20 |
|
value: 69.93690215204663 |
|
- type: mrr_at_3 |
|
value: 67.77777777777779 |
|
- type: mrr_at_5 |
|
value: 68.87222222222223 |
|
- type: nauc_map_at_1000_diff1 |
|
value: 70.84789011327231 |
|
- type: nauc_map_at_1000_max |
|
value: 60.852088181225824 |
|
- type: nauc_map_at_1000_std |
|
value: 6.549993568212846 |
|
- type: nauc_map_at_100_diff1 |
|
value: 70.84603146007751 |
|
- type: nauc_map_at_100_max |
|
value: 60.859417397516125 |
|
- type: nauc_map_at_100_std |
|
value: 6.577244018939677 |
|
- type: nauc_map_at_10_diff1 |
|
value: 70.71490936568583 |
|
- type: nauc_map_at_10_max |
|
value: 60.94472236517367 |
|
- type: nauc_map_at_10_std |
|
value: 6.53657697773106 |
|
- type: nauc_map_at_1_diff1 |
|
value: 74.59301032751448 |
|
- type: nauc_map_at_1_max |
|
value: 59.251209223705935 |
|
- type: nauc_map_at_1_std |
|
value: 6.536579330592454 |
|
- type: nauc_map_at_20_diff1 |
|
value: 70.69902333418673 |
|
- type: nauc_map_at_20_max |
|
value: 60.84819592450007 |
|
- type: nauc_map_at_20_std |
|
value: 6.487171209675751 |
|
- type: nauc_map_at_3_diff1 |
|
value: 70.94073456299253 |
|
- type: nauc_map_at_3_max |
|
value: 61.117845574972286 |
|
- type: nauc_map_at_3_std |
|
value: 5.824524654602759 |
|
- type: nauc_map_at_5_diff1 |
|
value: 70.64337838638826 |
|
- type: nauc_map_at_5_max |
|
value: 60.69375707294804 |
|
- type: nauc_map_at_5_std |
|
value: 6.1403804587682025 |
|
- type: nauc_mrr_at_1000_diff1 |
|
value: 70.84789011327231 |
|
- type: nauc_mrr_at_1000_max |
|
value: 60.852088181225824 |
|
- type: nauc_mrr_at_1000_std |
|
value: 6.549993568212846 |
|
- type: nauc_mrr_at_100_diff1 |
|
value: 70.84603146007751 |
|
- type: nauc_mrr_at_100_max |
|
value: 60.859417397516125 |
|
- type: nauc_mrr_at_100_std |
|
value: 6.577244018939677 |
|
- type: nauc_mrr_at_10_diff1 |
|
value: 70.71490936568583 |
|
- type: nauc_mrr_at_10_max |
|
value: 60.94472236517367 |
|
- type: nauc_mrr_at_10_std |
|
value: 6.53657697773106 |
|
- type: nauc_mrr_at_1_diff1 |
|
value: 74.59301032751448 |
|
- type: nauc_mrr_at_1_max |
|
value: 59.251209223705935 |
|
- type: nauc_mrr_at_1_std |
|
value: 6.536579330592454 |
|
- type: nauc_mrr_at_20_diff1 |
|
value: 70.69902333418673 |
|
- type: nauc_mrr_at_20_max |
|
value: 60.84819592450007 |
|
- type: nauc_mrr_at_20_std |
|
value: 6.487171209675751 |
|
- type: nauc_mrr_at_3_diff1 |
|
value: 70.94073456299253 |
|
- type: nauc_mrr_at_3_max |
|
value: 61.117845574972286 |
|
- type: nauc_mrr_at_3_std |
|
value: 5.824524654602759 |
|
- type: nauc_mrr_at_5_diff1 |
|
value: 70.64337838638826 |
|
- type: nauc_mrr_at_5_max |
|
value: 60.69375707294804 |
|
- type: nauc_mrr_at_5_std |
|
value: 6.1403804587682025 |
|
- type: nauc_ndcg_at_1000_diff1 |
|
value: 70.2568421673153 |
|
- type: nauc_ndcg_at_1000_max |
|
value: 61.154155762479746 |
|
- type: nauc_ndcg_at_1000_std |
|
value: 6.987492117976732 |
|
- type: nauc_ndcg_at_100_diff1 |
|
value: 70.23106290886678 |
|
- type: nauc_ndcg_at_100_max |
|
value: 61.387176821366296 |
|
- type: nauc_ndcg_at_100_std |
|
value: 7.782749694416603 |
|
- type: nauc_ndcg_at_10_diff1 |
|
value: 69.26227190907855 |
|
- type: nauc_ndcg_at_10_max |
|
value: 61.634434826859874 |
|
- type: nauc_ndcg_at_10_std |
|
value: 7.185316156791736 |
|
- type: nauc_ndcg_at_1_diff1 |
|
value: 74.59301032751448 |
|
- type: nauc_ndcg_at_1_max |
|
value: 59.251209223705935 |
|
- type: nauc_ndcg_at_1_std |
|
value: 6.536579330592454 |
|
- type: nauc_ndcg_at_20_diff1 |
|
value: 69.1954116973286 |
|
- type: nauc_ndcg_at_20_max |
|
value: 61.38887961478062 |
|
- type: nauc_ndcg_at_20_std |
|
value: 7.1318041010309585 |
|
- type: nauc_ndcg_at_3_diff1 |
|
value: 69.75775816678905 |
|
- type: nauc_ndcg_at_3_max |
|
value: 61.67436817540673 |
|
- type: nauc_ndcg_at_3_std |
|
value: 5.650531149732009 |
|
- type: nauc_ndcg_at_5_diff1 |
|
value: 69.1651947412561 |
|
- type: nauc_ndcg_at_5_max |
|
value: 60.97882565960433 |
|
- type: nauc_ndcg_at_5_std |
|
value: 6.203128058155249 |
|
- type: nauc_precision_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_precision_at_1000_max |
|
value: .nan |
|
- type: nauc_precision_at_1000_std |
|
value: .nan |
|
- type: nauc_precision_at_100_diff1 |
|
value: 68.65491294557121 |
|
- type: nauc_precision_at_100_max |
|
value: 80.36744109408565 |
|
- type: nauc_precision_at_100_std |
|
value: 70.92327126929257 |
|
- type: nauc_precision_at_10_diff1 |
|
value: 61.29162638094176 |
|
- type: nauc_precision_at_10_max |
|
value: 65.7264903076506 |
|
- type: nauc_precision_at_10_std |
|
value: 11.47548778748128 |
|
- type: nauc_precision_at_1_diff1 |
|
value: 74.59301032751448 |
|
- type: nauc_precision_at_1_max |
|
value: 59.251209223705935 |
|
- type: nauc_precision_at_1_std |
|
value: 6.536579330592454 |
|
- type: nauc_precision_at_20_diff1 |
|
value: 56.51478369125409 |
|
- type: nauc_precision_at_20_max |
|
value: 66.28882664176771 |
|
- type: nauc_precision_at_20_std |
|
value: 14.05415499533146 |
|
- type: nauc_precision_at_3_diff1 |
|
value: 65.55150000975934 |
|
- type: nauc_precision_at_3_max |
|
value: 63.631594870493636 |
|
- type: nauc_precision_at_3_std |
|
value: 5.057287295297996 |
|
- type: nauc_precision_at_5_diff1 |
|
value: 62.93787770906014 |
|
- type: nauc_precision_at_5_max |
|
value: 62.06285784899278 |
|
- type: nauc_precision_at_5_std |
|
value: 6.577948558011871 |
|
- type: nauc_recall_at_1000_diff1 |
|
value: .nan |
|
- type: nauc_recall_at_1000_max |
|
value: .nan |
|
- type: nauc_recall_at_1000_std |
|
value: .nan |
|
- type: nauc_recall_at_100_diff1 |
|
value: 68.6549129455701 |
|
- type: nauc_recall_at_100_max |
|
value: 80.36744109408454 |
|
- type: nauc_recall_at_100_std |
|
value: 70.92327126929207 |
|
- type: nauc_recall_at_10_diff1 |
|
value: 61.29162638094184 |
|
- type: nauc_recall_at_10_max |
|
value: 65.72649030765079 |
|
- type: nauc_recall_at_10_std |
|
value: 11.475487787481537 |
|
- type: nauc_recall_at_1_diff1 |
|
value: 74.59301032751448 |
|
- type: nauc_recall_at_1_max |
|
value: 59.251209223705935 |
|
- type: nauc_recall_at_1_std |
|
value: 6.536579330592454 |
|
- type: nauc_recall_at_20_diff1 |
|
value: 56.514783691254266 |
|
- type: nauc_recall_at_20_max |
|
value: 66.28882664176774 |
|
- type: nauc_recall_at_20_std |
|
value: 14.054154995331741 |
|
- type: nauc_recall_at_3_diff1 |
|
value: 65.55150000975928 |
|
- type: nauc_recall_at_3_max |
|
value: 63.63159487049364 |
|
- type: nauc_recall_at_3_std |
|
value: 5.05728729529798 |
|
- type: nauc_recall_at_5_diff1 |
|
value: 62.937877709060295 |
|
- type: nauc_recall_at_5_max |
|
value: 62.06285784899285 |
|
- type: nauc_recall_at_5_std |
|
value: 6.577948558011953 |
|
- type: ndcg_at_1 |
|
value: 60.778 |
|
- type: ndcg_at_10 |
|
value: 73.668 |
|
- type: ndcg_at_100 |
|
value: 76.21 |
|
- type: ndcg_at_1000 |
|
value: 76.459 |
|
- type: ndcg_at_20 |
|
value: 74.993 |
|
- type: ndcg_at_3 |
|
value: 70.00800000000001 |
|
- type: ndcg_at_5 |
|
value: 71.978 |
|
- type: precision_at_1 |
|
value: 60.778 |
|
- type: precision_at_10 |
|
value: 8.644 |
|
- type: precision_at_100 |
|
value: 0.9809999999999999 |
|
- type: precision_at_1000 |
|
value: 0.1 |
|
- type: precision_at_20 |
|
value: 4.583 |
|
- type: precision_at_3 |
|
value: 25.480999999999998 |
|
- type: precision_at_5 |
|
value: 16.244 |
|
- type: recall_at_1 |
|
value: 60.778 |
|
- type: recall_at_10 |
|
value: 86.444 |
|
- type: recall_at_100 |
|
value: 98.111 |
|
- type: recall_at_1000 |
|
value: 100.0 |
|
- type: recall_at_20 |
|
value: 91.667 |
|
- type: recall_at_3 |
|
value: 76.444 |
|
- type: recall_at_5 |
|
value: 81.22200000000001 |
|
task: |
|
type: Retrieval |
|
- dataset: |
|
config: eng_Latn-hun_Latn |
|
name: MTEB BibleNLPBitextMining (eng_Latn-hun_Latn) |
|
revision: 264a18480c529d9e922483839b4b9758e690b762 |
|
split: train |
|
type: davidstap/biblenlp-corpus-mmteb |
|
metrics: |
|
- type: accuracy |
|
value: 88.671875 |
|
- type: f1 |
|
value: 85.859375 |
|
- type: main_score |
|
value: 85.859375 |
|
- type: precision |
|
value: 84.71354166666667 |
|
- type: recall |
|
value: 88.671875 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-eng_Latn |
|
name: MTEB BibleNLPBitextMining (hun_Latn-eng_Latn) |
|
revision: 264a18480c529d9e922483839b4b9758e690b762 |
|
split: train |
|
type: davidstap/biblenlp-corpus-mmteb |
|
metrics: |
|
- type: accuracy |
|
value: 91.796875 |
|
- type: f1 |
|
value: 89.41406249999999 |
|
- type: main_score |
|
value: 89.41406249999999 |
|
- type: precision |
|
value: 88.31380208333334 |
|
- type: recall |
|
value: 91.796875 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: default |
|
name: MTEB HunSum2AbstractiveRetrieval (default) |
|
revision: 24e1445c8180d937f0a16f8ae8a62e77cc952e56 |
|
split: test |
|
type: SZTAKI-HLT/HunSum-2-abstractive |
|
metrics: |
|
- type: main_score |
|
value: 63.263000000000005 |
|
- type: map_at_1 |
|
value: 63.263000000000005 |
|
- type: map_at_10 |
|
value: 69.717 |
|
- type: map_at_100 |
|
value: 70.19999999999999 |
|
- type: map_at_1000 |
|
value: 70.223 |
|
- type: map_at_20 |
|
value: 69.987 |
|
- type: map_at_3 |
|
value: 68.126 |
|
- type: map_at_5 |
|
value: 69.11500000000001 |
|
- type: mrr_at_1 |
|
value: 63.263263263263255 |
|
- type: mrr_at_10 |
|
value: 69.71656179989505 |
|
- type: mrr_at_100 |
|
value: 70.20005091433352 |
|
- type: mrr_at_1000 |
|
value: 70.22300238535382 |
|
- type: mrr_at_20 |
|
value: 69.98650484718584 |
|
- type: mrr_at_3 |
|
value: 68.12645979312641 |
|
- type: mrr_at_5 |
|
value: 69.11494828161491 |
|
- type: nauc_map_at_1000_diff1 |
|
value: 78.57062147162597 |
|
- type: nauc_map_at_1000_max |
|
value: 67.50701502337495 |
|
- type: nauc_map_at_1000_std |
|
value: -0.5617129044803558 |
|
- type: nauc_map_at_100_diff1 |
|
value: 78.55994402867587 |
|
- type: nauc_map_at_100_max |
|
value: 67.50751346612932 |
|
- type: nauc_map_at_100_std |
|
value: -0.5527533150571393 |
|
- type: nauc_map_at_10_diff1 |
|
value: 78.40366721771652 |
|
- type: nauc_map_at_10_max |
|
value: 67.49241622659412 |
|
- type: nauc_map_at_10_std |
|
value: -0.48552097268197614 |
|
- type: nauc_map_at_1_diff1 |
|
value: 82.01486923813978 |
|
- type: nauc_map_at_1_max |
|
value: 65.96265600324601 |
|
- type: nauc_map_at_1_std |
|
value: -3.3920974069100702 |
|
- type: nauc_map_at_20_diff1 |
|
value: 78.47160921094391 |
|
- type: nauc_map_at_20_max |
|
value: 67.53010937556571 |
|
- type: nauc_map_at_20_std |
|
value: -0.5304810036230149 |
|
- type: nauc_map_at_3_diff1 |
|
value: 78.82728109994231 |
|
- type: nauc_map_at_3_max |
|
value: 67.67886259360823 |
|
- type: nauc_map_at_3_std |
|
value: -0.8390404611287001 |
|
- type: nauc_map_at_5_diff1 |
|
value: 78.64851152021848 |
|
- type: nauc_map_at_5_max |
|
value: 67.56443643847581 |
|
- type: nauc_map_at_5_std |
|
value: -0.5438994708241538 |
|
- type: nauc_mrr_at_1000_diff1 |
|
value: 78.57062147162597 |
|
- type: nauc_mrr_at_1000_max |
|
value: 67.50701502337495 |
|
- type: nauc_mrr_at_1000_std |
|
value: -0.5617129044803558 |
|
- type: nauc_mrr_at_100_diff1 |
|
value: 78.55994402867587 |
|
- type: nauc_mrr_at_100_max |
|
value: 67.50751346612932 |
|
- type: nauc_mrr_at_100_std |
|
value: -0.5527533150571393 |
|
- type: nauc_mrr_at_10_diff1 |
|
value: 78.40366721771652 |
|
- type: nauc_mrr_at_10_max |
|
value: 67.49241622659412 |
|
- type: nauc_mrr_at_10_std |
|
value: -0.48552097268197614 |
|
- type: nauc_mrr_at_1_diff1 |
|
value: 82.01486923813978 |
|
- type: nauc_mrr_at_1_max |
|
value: 65.96265600324601 |
|
- type: nauc_mrr_at_1_std |
|
value: -3.3920974069100702 |
|
- type: nauc_mrr_at_20_diff1 |
|
value: 78.47160921094391 |
|
- type: nauc_mrr_at_20_max |
|
value: 67.53010937556571 |
|
- type: nauc_mrr_at_20_std |
|
value: -0.5304810036230149 |
|
- type: nauc_mrr_at_3_diff1 |
|
value: 78.82728109994231 |
|
- type: nauc_mrr_at_3_max |
|
value: 67.67886259360823 |
|
- type: nauc_mrr_at_3_std |
|
value: -0.8390404611287001 |
|
- type: nauc_mrr_at_5_diff1 |
|
value: 78.64851152021848 |
|
- type: nauc_mrr_at_5_max |
|
value: 67.56443643847581 |
|
- type: nauc_mrr_at_5_std |
|
value: -0.5438994708241538 |
|
- type: nauc_ndcg_at_1000_diff1 |
|
value: 77.85313935589254 |
|
- type: nauc_ndcg_at_1000_max |
|
value: 67.79745016701565 |
|
- type: nauc_ndcg_at_1000_std |
|
value: 0.3743893992928968 |
|
- type: nauc_ndcg_at_100_diff1 |
|
value: 77.54895730138853 |
|
- type: nauc_ndcg_at_100_max |
|
value: 67.90017248869928 |
|
- type: nauc_ndcg_at_100_std |
|
value: 0.859162358234398 |
|
- type: nauc_ndcg_at_10_diff1 |
|
value: 76.71113405671676 |
|
- type: nauc_ndcg_at_10_max |
|
value: 67.96034182778398 |
|
- type: nauc_ndcg_at_10_std |
|
value: 1.1822837192182254 |
|
- type: nauc_ndcg_at_1_diff1 |
|
value: 82.01486923813978 |
|
- type: nauc_ndcg_at_1_max |
|
value: 65.96265600324601 |
|
- type: nauc_ndcg_at_1_std |
|
value: -3.3920974069100702 |
|
- type: nauc_ndcg_at_20_diff1 |
|
value: 76.93959621702203 |
|
- type: nauc_ndcg_at_20_max |
|
value: 68.11195662698223 |
|
- type: nauc_ndcg_at_20_std |
|
value: 1.04309687394849 |
|
- type: nauc_ndcg_at_3_diff1 |
|
value: 77.79565059957739 |
|
- type: nauc_ndcg_at_3_max |
|
value: 68.28729385816999 |
|
- type: nauc_ndcg_at_3_std |
|
value: 0.2325515867720005 |
|
- type: nauc_ndcg_at_5_diff1 |
|
value: 77.37740780039985 |
|
- type: nauc_ndcg_at_5_max |
|
value: 68.0591693716456 |
|
- type: nauc_ndcg_at_5_std |
|
value: 0.8419316054801026 |
|
- type: nauc_precision_at_1000_diff1 |
|
value: 70.06119288295852 |
|
- type: nauc_precision_at_1000_max |
|
value: 56.300969751588504 |
|
- type: nauc_precision_at_1000_std |
|
value: 42.8131104675957 |
|
- type: nauc_precision_at_100_diff1 |
|
value: 67.53252742986358 |
|
- type: nauc_precision_at_100_max |
|
value: 71.63984328411749 |
|
- type: nauc_precision_at_100_std |
|
value: 20.467710864542678 |
|
- type: nauc_precision_at_10_diff1 |
|
value: 68.62375685620702 |
|
- type: nauc_precision_at_10_max |
|
value: 70.02532507228068 |
|
- type: nauc_precision_at_10_std |
|
value: 9.35439782317633 |
|
- type: nauc_precision_at_1_diff1 |
|
value: 82.01486923813978 |
|
- type: nauc_precision_at_1_max |
|
value: 65.96265600324601 |
|
- type: nauc_precision_at_1_std |
|
value: -3.3920974069100702 |
|
- type: nauc_precision_at_20_diff1 |
|
value: 67.96187481073133 |
|
- type: nauc_precision_at_20_max |
|
value: 71.59854027319963 |
|
- type: nauc_precision_at_20_std |
|
value: 10.641909874113086 |
|
- type: nauc_precision_at_3_diff1 |
|
value: 74.38802810704372 |
|
- type: nauc_precision_at_3_max |
|
value: 70.31804260818862 |
|
- type: nauc_precision_at_3_std |
|
value: 3.8694413447531946 |
|
- type: nauc_precision_at_5_diff1 |
|
value: 72.53680275396366 |
|
- type: nauc_precision_at_5_max |
|
value: 69.84127154759457 |
|
- type: nauc_precision_at_5_std |
|
value: 6.232801743816592 |
|
- type: nauc_recall_at_1000_diff1 |
|
value: 70.06119288296337 |
|
- type: nauc_recall_at_1000_max |
|
value: 56.30096975158339 |
|
- type: nauc_recall_at_1000_std |
|
value: 42.81311046760523 |
|
- type: nauc_recall_at_100_diff1 |
|
value: 67.53252742986345 |
|
- type: nauc_recall_at_100_max |
|
value: 71.63984328411706 |
|
- type: nauc_recall_at_100_std |
|
value: 20.46771086454334 |
|
- type: nauc_recall_at_10_diff1 |
|
value: 68.62375685620707 |
|
- type: nauc_recall_at_10_max |
|
value: 70.02532507228068 |
|
- type: nauc_recall_at_10_std |
|
value: 9.354397823176459 |
|
- type: nauc_recall_at_1_diff1 |
|
value: 82.01486923813978 |
|
- type: nauc_recall_at_1_max |
|
value: 65.96265600324601 |
|
- type: nauc_recall_at_1_std |
|
value: -3.3920974069100702 |
|
- type: nauc_recall_at_20_diff1 |
|
value: 67.96187481073152 |
|
- type: nauc_recall_at_20_max |
|
value: 71.59854027319979 |
|
- type: nauc_recall_at_20_std |
|
value: 10.641909874113258 |
|
- type: nauc_recall_at_3_diff1 |
|
value: 74.3880281070437 |
|
- type: nauc_recall_at_3_max |
|
value: 70.31804260818865 |
|
- type: nauc_recall_at_3_std |
|
value: 3.8694413447530995 |
|
- type: nauc_recall_at_5_diff1 |
|
value: 72.53680275396374 |
|
- type: nauc_recall_at_5_max |
|
value: 69.84127154759464 |
|
- type: nauc_recall_at_5_std |
|
value: 6.232801743816686 |
|
- type: ndcg_at_1 |
|
value: 63.263000000000005 |
|
- type: ndcg_at_10 |
|
value: 72.89099999999999 |
|
- type: ndcg_at_100 |
|
value: 75.421 |
|
- type: ndcg_at_1000 |
|
value: 76.027 |
|
- type: ndcg_at_20 |
|
value: 73.919 |
|
- type: ndcg_at_3 |
|
value: 69.646 |
|
- type: ndcg_at_5 |
|
value: 71.434 |
|
- type: precision_at_1 |
|
value: 63.263000000000005 |
|
- type: precision_at_10 |
|
value: 8.288 |
|
- type: precision_at_100 |
|
value: 0.95 |
|
- type: precision_at_1000 |
|
value: 0.1 |
|
- type: precision_at_20 |
|
value: 4.352 |
|
- type: precision_at_3 |
|
value: 24.675 |
|
- type: precision_at_5 |
|
value: 15.676000000000002 |
|
- type: recall_at_1 |
|
value: 63.263000000000005 |
|
- type: recall_at_10 |
|
value: 82.883 |
|
- type: recall_at_100 |
|
value: 95.045 |
|
- type: recall_at_1000 |
|
value: 99.8 |
|
- type: recall_at_20 |
|
value: 87.03699999999999 |
|
- type: recall_at_3 |
|
value: 74.024 |
|
- type: recall_at_5 |
|
value: 78.378 |
|
task: |
|
type: Retrieval |
|
- dataset: |
|
config: hu |
|
name: MTEB MassiveIntentClassification (hu) |
|
revision: 4672e20407010da34463acc759c162ca9734bca6 |
|
split: test |
|
type: mteb/amazon_massive_intent |
|
metrics: |
|
- type: accuracy |
|
value: 60.08406186953599 |
|
- type: f1 |
|
value: 56.958742875652455 |
|
- type: f1_weighted |
|
value: 60.57068245324919 |
|
- type: main_score |
|
value: 60.08406186953599 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hu |
|
name: MTEB MassiveIntentClassification (hu) |
|
revision: 4672e20407010da34463acc759c162ca9734bca6 |
|
split: validation |
|
type: mteb/amazon_massive_intent |
|
metrics: |
|
- type: accuracy |
|
value: 60.201672405312344 |
|
- type: f1 |
|
value: 57.03816512332761 |
|
- type: f1_weighted |
|
value: 60.53109947438201 |
|
- type: main_score |
|
value: 60.201672405312344 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hu |
|
name: MTEB MassiveScenarioClassification (hu) |
|
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 |
|
split: test |
|
type: mteb/amazon_massive_scenario |
|
metrics: |
|
- type: accuracy |
|
value: 66.61398789509079 |
|
- type: f1 |
|
value: 65.88647044935249 |
|
- type: f1_weighted |
|
value: 66.80145146976484 |
|
- type: main_score |
|
value: 66.61398789509079 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hu |
|
name: MTEB MassiveScenarioClassification (hu) |
|
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8 |
|
split: validation |
|
type: mteb/amazon_massive_scenario |
|
metrics: |
|
- type: accuracy |
|
value: 66.11411706837187 |
|
- type: f1 |
|
value: 65.76717397996951 |
|
- type: f1_weighted |
|
value: 66.29902597756885 |
|
- type: main_score |
|
value: 66.11411706837187 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hu |
|
name: MTEB MultiEURLEXMultilabelClassification (hu) |
|
revision: 2aea5a6dc8fdcfeca41d0fb963c0a338930bde5c |
|
split: test |
|
type: mteb/eurlex-multilingual |
|
metrics: |
|
- type: accuracy |
|
value: 3.0839999999999996 |
|
- type: f1 |
|
value: 27.860225486785566 |
|
- type: lrap |
|
value: 43.02579150793552 |
|
- type: main_score |
|
value: 3.0839999999999996 |
|
task: |
|
type: MultilabelClassification |
|
- dataset: |
|
config: arb_Arab-hun_Latn |
|
name: MTEB NTREXBitextMining (arb_Arab-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 85.678517776665 |
|
- type: f1 |
|
value: 81.92049979731502 |
|
- type: main_score |
|
value: 81.92049979731502 |
|
- type: precision |
|
value: 80.21115005842097 |
|
- type: recall |
|
value: 85.678517776665 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: ben_Beng-hun_Latn |
|
name: MTEB NTREXBitextMining (ben_Beng-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 44.566850275413124 |
|
- type: f1 |
|
value: 39.07033025889276 |
|
- type: main_score |
|
value: 39.07033025889276 |
|
- type: precision |
|
value: 37.07348327291399 |
|
- type: recall |
|
value: 44.566850275413124 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: deu_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (deu_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.44016024036054 |
|
- type: f1 |
|
value: 91.61909530963112 |
|
- type: main_score |
|
value: 91.61909530963112 |
|
- type: precision |
|
value: 90.75279586045735 |
|
- type: recall |
|
value: 93.44016024036054 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: ell_Grek-hun_Latn |
|
name: MTEB NTREXBitextMining (ell_Grek-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.4371557336004 |
|
- type: f1 |
|
value: 89.0261582850466 |
|
- type: main_score |
|
value: 89.0261582850466 |
|
- type: precision |
|
value: 87.9043565348022 |
|
- type: recall |
|
value: 91.4371557336004 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: eng_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (eng_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 94.44166249374061 |
|
- type: f1 |
|
value: 92.8092138207311 |
|
- type: main_score |
|
value: 92.8092138207311 |
|
- type: precision |
|
value: 92.0422300116842 |
|
- type: recall |
|
value: 94.44166249374061 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: fas_Arab-hun_Latn |
|
name: MTEB NTREXBitextMining (fas_Arab-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 89.53430145217827 |
|
- type: f1 |
|
value: 86.72270310227245 |
|
- type: main_score |
|
value: 86.72270310227245 |
|
- type: precision |
|
value: 85.42814221331997 |
|
- type: recall |
|
value: 89.53430145217827 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: fin_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (fin_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.98647971957938 |
|
- type: f1 |
|
value: 88.44600233683859 |
|
- type: main_score |
|
value: 88.44600233683859 |
|
- type: precision |
|
value: 87.2575529961609 |
|
- type: recall |
|
value: 90.98647971957938 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: fra_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (fra_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 92.28843264897347 |
|
- type: f1 |
|
value: 90.12518778167251 |
|
- type: main_score |
|
value: 90.12518778167251 |
|
- type: precision |
|
value: 89.12535469871473 |
|
- type: recall |
|
value: 92.28843264897347 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: heb_Hebr-hun_Latn |
|
name: MTEB NTREXBitextMining (heb_Hebr-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 87.33099649474211 |
|
- type: f1 |
|
value: 83.88582874311467 |
|
- type: main_score |
|
value: 83.88582874311467 |
|
- type: precision |
|
value: 82.31263562009681 |
|
- type: recall |
|
value: 87.33099649474211 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hin_Deva-hun_Latn |
|
name: MTEB NTREXBitextMining (hin_Deva-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 86.52979469203805 |
|
- type: f1 |
|
value: 83.08240137984755 |
|
- type: main_score |
|
value: 83.08240137984755 |
|
- type: precision |
|
value: 81.51352028042064 |
|
- type: recall |
|
value: 86.52979469203805 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-arb_Arab |
|
name: MTEB NTREXBitextMining (hun_Latn-arb_Arab) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 86.73009514271406 |
|
- type: f1 |
|
value: 83.12397167179341 |
|
- type: main_score |
|
value: 83.12397167179341 |
|
- type: precision |
|
value: 81.47805040894676 |
|
- type: recall |
|
value: 86.73009514271406 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-ben_Beng |
|
name: MTEB NTREXBitextMining (hun_Latn-ben_Beng) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 41.16174261392088 |
|
- type: f1 |
|
value: 32.73025519520262 |
|
- type: main_score |
|
value: 32.73025519520262 |
|
- type: precision |
|
value: 29.859172986363774 |
|
- type: recall |
|
value: 41.16174261392088 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-deu_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-deu_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.39008512769153 |
|
- type: f1 |
|
value: 91.5456518110499 |
|
- type: main_score |
|
value: 91.5456518110499 |
|
- type: precision |
|
value: 90.66099148723085 |
|
- type: recall |
|
value: 93.39008512769153 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-ell_Grek |
|
name: MTEB NTREXBitextMining (hun_Latn-ell_Grek) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 92.03805708562844 |
|
- type: f1 |
|
value: 89.81305291270239 |
|
- type: main_score |
|
value: 89.81305291270239 |
|
- type: precision |
|
value: 88.78317476214322 |
|
- type: recall |
|
value: 92.03805708562844 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-eng_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-eng_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 94.74211316975463 |
|
- type: f1 |
|
value: 93.23985978968453 |
|
- type: main_score |
|
value: 93.23985978968453 |
|
- type: precision |
|
value: 92.51377065598398 |
|
- type: recall |
|
value: 94.74211316975463 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-fas_Arab |
|
name: MTEB NTREXBitextMining (hun_Latn-fas_Arab) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 88.5327991987982 |
|
- type: f1 |
|
value: 85.49240527457853 |
|
- type: main_score |
|
value: 85.49240527457853 |
|
- type: precision |
|
value: 84.10413238905979 |
|
- type: recall |
|
value: 88.5327991987982 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-fin_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-fin_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.23535302954431 |
|
- type: f1 |
|
value: 87.53296611584042 |
|
- type: main_score |
|
value: 87.53296611584042 |
|
- type: precision |
|
value: 86.26690035052579 |
|
- type: recall |
|
value: 90.23535302954431 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-fra_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-fra_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 92.63895843765648 |
|
- type: f1 |
|
value: 90.47070605908863 |
|
- type: main_score |
|
value: 90.47070605908863 |
|
- type: precision |
|
value: 89.42163244867301 |
|
- type: recall |
|
value: 92.63895843765648 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-heb_Hebr |
|
name: MTEB NTREXBitextMining (hun_Latn-heb_Hebr) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 86.62994491737606 |
|
- type: f1 |
|
value: 83.19388173168845 |
|
- type: main_score |
|
value: 83.19388173168845 |
|
- type: precision |
|
value: 81.65832081455517 |
|
- type: recall |
|
value: 86.62994491737606 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-hin_Deva |
|
name: MTEB NTREXBitextMining (hun_Latn-hin_Deva) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 83.97596394591888 |
|
- type: f1 |
|
value: 79.85502062617736 |
|
- type: main_score |
|
value: 79.85502062617736 |
|
- type: precision |
|
value: 78.01758192844824 |
|
- type: recall |
|
value: 83.97596394591888 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-ind_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-ind_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 92.68903355032549 |
|
- type: f1 |
|
value: 90.64596895343014 |
|
- type: main_score |
|
value: 90.64596895343014 |
|
- type: precision |
|
value: 89.68869971624103 |
|
- type: recall |
|
value: 92.68903355032549 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-jpn_Jpan |
|
name: MTEB NTREXBitextMining (hun_Latn-jpn_Jpan) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 85.778668002003 |
|
- type: f1 |
|
value: 82.19829744616925 |
|
- type: main_score |
|
value: 82.19829744616925 |
|
- type: precision |
|
value: 80.62426973794025 |
|
- type: recall |
|
value: 85.778668002003 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-kor_Hang |
|
name: MTEB NTREXBitextMining (hun_Latn-kor_Hang) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 84.17626439659489 |
|
- type: f1 |
|
value: 80.26746468909714 |
|
- type: main_score |
|
value: 80.26746468909714 |
|
- type: precision |
|
value: 78.5646097351155 |
|
- type: recall |
|
value: 84.17626439659489 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-lav_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-lav_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.1352028042063 |
|
- type: f1 |
|
value: 87.30262059756302 |
|
- type: main_score |
|
value: 87.30262059756302 |
|
- type: precision |
|
value: 85.98731430479052 |
|
- type: recall |
|
value: 90.1352028042063 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-lit_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-lit_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 89.58437656484726 |
|
- type: f1 |
|
value: 86.8252378567852 |
|
- type: main_score |
|
value: 86.8252378567852 |
|
- type: precision |
|
value: 85.54581872809214 |
|
- type: recall |
|
value: 89.58437656484726 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-nld_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-nld_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.03955933900852 |
|
- type: f1 |
|
value: 91.03989317309296 |
|
- type: main_score |
|
value: 91.03989317309296 |
|
- type: precision |
|
value: 90.08930061759305 |
|
- type: recall |
|
value: 93.03955933900852 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-pol_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-pol_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.58738107160741 |
|
- type: f1 |
|
value: 89.28225671841095 |
|
- type: main_score |
|
value: 89.28225671841095 |
|
- type: precision |
|
value: 88.18227341011517 |
|
- type: recall |
|
value: 91.58738107160741 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-por_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-por_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.59038557836755 |
|
- type: f1 |
|
value: 91.71256885327992 |
|
- type: main_score |
|
value: 91.71256885327992 |
|
- type: precision |
|
value: 90.80287097312635 |
|
- type: recall |
|
value: 93.59038557836755 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-rus_Cyrl |
|
name: MTEB NTREXBitextMining (hun_Latn-rus_Cyrl) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.3370055082624 |
|
- type: f1 |
|
value: 88.88916708395926 |
|
- type: main_score |
|
value: 88.88916708395926 |
|
- type: precision |
|
value: 87.75961561389704 |
|
- type: recall |
|
value: 91.3370055082624 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-spa_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-spa_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.69053580370556 |
|
- type: f1 |
|
value: 91.94959105324652 |
|
- type: main_score |
|
value: 91.94959105324652 |
|
- type: precision |
|
value: 91.12418627941913 |
|
- type: recall |
|
value: 93.69053580370556 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-swa_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-swa_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 35.803705558337505 |
|
- type: f1 |
|
value: 27.79832969518814 |
|
- type: main_score |
|
value: 27.79832969518814 |
|
- type: precision |
|
value: 25.370895920971037 |
|
- type: recall |
|
value: 35.803705558337505 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-swe_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-swe_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.59038557836755 |
|
- type: f1 |
|
value: 91.66249374061091 |
|
- type: main_score |
|
value: 91.66249374061091 |
|
- type: precision |
|
value: 90.74445000834585 |
|
- type: recall |
|
value: 93.59038557836755 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-tam_Taml |
|
name: MTEB NTREXBitextMining (hun_Latn-tam_Taml) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 27.391086629944915 |
|
- type: f1 |
|
value: 19.094552675413095 |
|
- type: main_score |
|
value: 19.094552675413095 |
|
- type: precision |
|
value: 16.88288208814635 |
|
- type: recall |
|
value: 27.391086629944915 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-tur_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-tur_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.48723084626941 |
|
- type: f1 |
|
value: 89.11700884660323 |
|
- type: main_score |
|
value: 89.11700884660323 |
|
- type: precision |
|
value: 87.99031881155067 |
|
- type: recall |
|
value: 91.48723084626941 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-vie_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-vie_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.13670505758637 |
|
- type: f1 |
|
value: 88.6696711734268 |
|
- type: main_score |
|
value: 88.6696711734268 |
|
- type: precision |
|
value: 87.49374061091638 |
|
- type: recall |
|
value: 91.13670505758637 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-zho_Hant |
|
name: MTEB NTREXBitextMining (hun_Latn-zho_Hant) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 89.33400100150224 |
|
- type: f1 |
|
value: 86.55745523046474 |
|
- type: main_score |
|
value: 86.55745523046474 |
|
- type: precision |
|
value: 85.29794692038057 |
|
- type: recall |
|
value: 89.33400100150224 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn-zul_Latn |
|
name: MTEB NTREXBitextMining (hun_Latn-zul_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 16.675012518778168 |
|
- type: f1 |
|
value: 11.21636405139599 |
|
- type: main_score |
|
value: 11.21636405139599 |
|
- type: precision |
|
value: 9.903070059112947 |
|
- type: recall |
|
value: 16.675012518778168 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: ind_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (ind_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 92.93940911367051 |
|
- type: f1 |
|
value: 90.96478050408946 |
|
- type: main_score |
|
value: 90.96478050408946 |
|
- type: precision |
|
value: 90.03922550492406 |
|
- type: recall |
|
value: 92.93940911367051 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: jpn_Jpan-hun_Latn |
|
name: MTEB NTREXBitextMining (jpn_Jpan-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 88.28242363545317 |
|
- type: f1 |
|
value: 85.11433817392756 |
|
- type: main_score |
|
value: 85.11433817392756 |
|
- type: precision |
|
value: 83.67551326990485 |
|
- type: recall |
|
value: 88.28242363545317 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: kor_Hang-hun_Latn |
|
name: MTEB NTREXBitextMining (kor_Hang-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 85.778668002003 |
|
- type: f1 |
|
value: 81.83608746453012 |
|
- type: main_score |
|
value: 81.83608746453012 |
|
- type: precision |
|
value: 80.0233683859122 |
|
- type: recall |
|
value: 85.778668002003 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: lav_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (lav_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.73760640961443 |
|
- type: f1 |
|
value: 89.42914371557336 |
|
- type: main_score |
|
value: 89.42914371557336 |
|
- type: precision |
|
value: 88.32832582206642 |
|
- type: recall |
|
value: 91.73760640961443 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: lit_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (lit_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.78768152228342 |
|
- type: f1 |
|
value: 89.50926389584376 |
|
- type: main_score |
|
value: 89.50926389584376 |
|
- type: precision |
|
value: 88.39926556501419 |
|
- type: recall |
|
value: 91.78768152228342 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: nld_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (nld_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.49023535302955 |
|
- type: f1 |
|
value: 91.6190953096311 |
|
- type: main_score |
|
value: 91.6190953096311 |
|
- type: precision |
|
value: 90.72775830412286 |
|
- type: recall |
|
value: 93.49023535302955 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: pol_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (pol_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 91.28693039559339 |
|
- type: f1 |
|
value: 88.99515940577533 |
|
- type: main_score |
|
value: 88.99515940577533 |
|
- type: precision |
|
value: 87.9293940911367 |
|
- type: recall |
|
value: 91.28693039559339 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: por_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (por_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.03955933900852 |
|
- type: f1 |
|
value: 91.08496077449509 |
|
- type: main_score |
|
value: 91.08496077449509 |
|
- type: precision |
|
value: 90.17860123518612 |
|
- type: recall |
|
value: 93.03955933900852 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: rus_Cyrl-hun_Latn |
|
name: MTEB NTREXBitextMining (rus_Cyrl-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.98647971957938 |
|
- type: f1 |
|
value: 88.43932565514937 |
|
- type: main_score |
|
value: 88.43932565514937 |
|
- type: precision |
|
value: 87.2475379736271 |
|
- type: recall |
|
value: 90.98647971957938 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: spa_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (spa_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.23985978968453 |
|
- type: f1 |
|
value: 91.3386746786847 |
|
- type: main_score |
|
value: 91.3386746786847 |
|
- type: precision |
|
value: 90.43148055416457 |
|
- type: recall |
|
value: 93.23985978968453 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: swa_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (swa_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 35.95393089634452 |
|
- type: f1 |
|
value: 30.612257939034187 |
|
- type: main_score |
|
value: 30.612257939034187 |
|
- type: precision |
|
value: 28.995078568906944 |
|
- type: recall |
|
value: 35.95393089634452 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: swe_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (swe_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 93.64046069103655 |
|
- type: f1 |
|
value: 91.86613253213153 |
|
- type: main_score |
|
value: 91.86613253213153 |
|
- type: precision |
|
value: 91.04072775830413 |
|
- type: recall |
|
value: 93.64046069103655 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: tam_Taml-hun_Latn |
|
name: MTEB NTREXBitextMining (tam_Taml-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 29.04356534802203 |
|
- type: f1 |
|
value: 25.164093122029808 |
|
- type: main_score |
|
value: 25.164093122029808 |
|
- type: precision |
|
value: 23.849573878565543 |
|
- type: recall |
|
value: 29.04356534802203 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: tur_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (tur_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.83625438157236 |
|
- type: f1 |
|
value: 88.36087464530128 |
|
- type: main_score |
|
value: 88.36087464530128 |
|
- type: precision |
|
value: 87.19829744616925 |
|
- type: recall |
|
value: 90.83625438157236 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: vie_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (vie_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.68602904356536 |
|
- type: f1 |
|
value: 88.10882991153397 |
|
- type: main_score |
|
value: 88.10882991153397 |
|
- type: precision |
|
value: 86.90118511099983 |
|
- type: recall |
|
value: 90.68602904356536 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: zho_Hant-hun_Latn |
|
name: MTEB NTREXBitextMining (zho_Hant-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 90.1352028042063 |
|
- type: f1 |
|
value: 87.46035720247039 |
|
- type: main_score |
|
value: 87.46035720247039 |
|
- type: precision |
|
value: 86.19810668383528 |
|
- type: recall |
|
value: 90.1352028042063 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: zul_Latn-hun_Latn |
|
name: MTEB NTREXBitextMining (zul_Latn-hun_Latn) |
|
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33 |
|
split: test |
|
type: mteb/NTREX |
|
metrics: |
|
- type: accuracy |
|
value: 17.1256885327992 |
|
- type: f1 |
|
value: 13.692538409811572 |
|
- type: main_score |
|
value: 13.692538409811572 |
|
- type: precision |
|
value: 12.811084017018844 |
|
- type: recall |
|
value: 17.1256885327992 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: rom-hun |
|
name: MTEB RomaTalesBitextMining (rom-hun) |
|
revision: f4394dbca6845743cd33eba77431767b232ef489 |
|
split: test |
|
type: kardosdrur/roma-tales |
|
metrics: |
|
- type: accuracy |
|
value: 6.046511627906977 |
|
- type: f1 |
|
value: 2.950830564784053 |
|
- type: main_score |
|
value: 2.950830564784053 |
|
- type: precision |
|
value: 2.295127353266888 |
|
- type: recall |
|
value: 6.046511627906977 |
|
task: |
|
type: BitextMining |
|
- dataset: |
|
config: hun_Latn |
|
name: MTEB SIB200Classification (hun_Latn) |
|
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b |
|
split: test |
|
type: mteb/sib200 |
|
metrics: |
|
- type: accuracy |
|
value: 72.74509803921569 |
|
- type: f1 |
|
value: 71.6748881571977 |
|
- type: f1_weighted |
|
value: 72.7699432186266 |
|
- type: main_score |
|
value: 72.74509803921569 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hun_Latn |
|
name: MTEB SIB200Classification (hun_Latn) |
|
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b |
|
split: train |
|
type: mteb/sib200 |
|
metrics: |
|
- type: accuracy |
|
value: 71.92582025677605 |
|
- type: f1 |
|
value: 70.9175403606058 |
|
- type: f1_weighted |
|
value: 71.9988920000764 |
|
- type: main_score |
|
value: 71.92582025677605 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hun_Latn |
|
name: MTEB SIB200Classification (hun_Latn) |
|
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b |
|
split: validation |
|
type: mteb/sib200 |
|
metrics: |
|
- type: accuracy |
|
value: 66.76767676767676 |
|
- type: f1 |
|
value: 66.07599012119566 |
|
- type: f1_weighted |
|
value: 67.15823510190054 |
|
- type: main_score |
|
value: 66.76767676767676 |
|
task: |
|
type: Classification |
|
- dataset: |
|
config: hun_Latn |
|
name: MTEB SIB200ClusteringS2S (hun_Latn) |
|
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b |
|
split: test |
|
type: mteb/sib200 |
|
metrics: |
|
- type: main_score |
|
value: 39.24288169703154 |
|
- type: v_measure |
|
value: 39.24288169703154 |
|
- type: v_measure_std |
|
value: 2.214708184335194 |
|
task: |
|
type: Clustering |
|
- dataset: |
|
config: hun-eng |
|
name: MTEB Tatoeba (hun-eng) |
|
revision: 69e8f12da6e31d59addadda9a9c8a2e601a0e282 |
|
split: test |
|
type: mteb/tatoeba-bitext-mining |
|
metrics: |
|
- type: accuracy |
|
value: 91.0 |
|
- type: f1 |
|
value: 88.47999999999999 |
|
- type: main_score |
|
value: 88.47999999999999 |
|
- type: precision |
|
value: 87.3 |
|
- type: recall |
|
value: 91.0 |
|
task: |
|
type: BitextMining |
|
tags: |
|
- mteb |
|
--- |
|
|
|
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 |
|
language: |
|
- hu |
|
library_name: sentence-transformers |
|
license: apache-2.0 |
|
metrics: |
|
- cosine_accuracy |
|
- dot_accuracy |
|
- manhattan_accuracy |
|
- euclidean_accuracy |
|
- max_accuracy |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
- generated_from_trainer |
|
- dataset_size:857856 |
|
- loss:MultipleNegativesRankingLoss |
|
widget: |
|
- source_sentence: Emberek várnak a lámpánál kerékpárral. |
|
sentences: |
|
- Az emberek piros lámpánál haladnak. |
|
- Az emberek a kerékpárjukon vannak. |
|
- Egy fekete kutya úszik a vízben egy teniszlabdával a szájában |
|
- source_sentence: A kutya a vízben van. |
|
sentences: |
|
- Két férfi takarítja a havat a tetőről, az egyik egy emelőben ül, a másik pedig |
|
a tetőn. |
|
- A macska a vízben van, és dühös. |
|
- Egy kutya van a vízben, a szájában egy faág. |
|
- source_sentence: A nő feketét visel. |
|
sentences: |
|
- Egy barna kutya fröcsköl, ahogy úszik a vízben. |
|
- Egy tetoválással rendelkező nő, aki fekete tank tetején néz a földre. |
|
- 'Egy kékbe öltözött nő intenzív arckifejezéssel üti a teniszlabdát. A képen:' |
|
- source_sentence: Az emberek alszanak. |
|
sentences: |
|
- Három ember beszélget egy városi utcán. |
|
- A nő fehéret visel. |
|
- Egy apa és a fia ölelgeti alvás közben. |
|
- source_sentence: Az emberek alszanak. |
|
sentences: |
|
- Egy feketébe öltözött nő cigarettát és bevásárlótáskát tart a kezében, miközben |
|
egy idősebb nő átmegy az utcán. |
|
- Egy csoport ember ül egy nyitott, térszerű területen, mögötte nagy bokrok és egy |
|
sor viktoriánus stílusú épület, melyek közül sokat a kép jobb oldalán lévő erős |
|
elmosódás tesz kivehetetlenné. |
|
- Egy apa és a fia ölelgeti alvás közben. |
|
model-index: |
|
- name: paraphrase-multilingual-MiniLM-L12-hu-v1 |
|
results: |
|
- task: |
|
type: triplet |
|
name: Triplet |
|
dataset: |
|
name: all nli dev |
|
type: all-nli-dev |
|
metrics: |
|
- type: cosine_accuracy |
|
value: 0.992 |
|
name: Cosine Accuracy |
|
- type: dot_accuracy |
|
value: 0.0108 |
|
name: Dot Accuracy |
|
- type: manhattan_accuracy |
|
value: 0.9908 |
|
name: Manhattan Accuracy |
|
- type: euclidean_accuracy |
|
value: 0.9908 |
|
name: Euclidean Accuracy |
|
- type: max_accuracy |
|
value: 0.992 |
|
name: Max Accuracy |
|
- task: |
|
type: triplet |
|
name: Triplet |
|
dataset: |
|
name: all nli test |
|
type: all-nli-test |
|
metrics: |
|
- type: cosine_accuracy |
|
value: 0.9913636363636363 |
|
name: Cosine Accuracy |
|
- type: dot_accuracy |
|
value: 0.013939393939393939 |
|
name: Dot Accuracy |
|
- type: manhattan_accuracy |
|
value: 0.990909090909091 |
|
name: Manhattan Accuracy |
|
- type: euclidean_accuracy |
|
value: 0.9910606060606061 |
|
name: Euclidean Accuracy |
|
- type: max_accuracy |
|
value: 0.9913636363636363 |
|
name: Max Accuracy |
|
|
|
# paraphrase-multilingual-MiniLM-L12-v2 |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the train dataset. It maps sentences & paragraphs to a 384-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-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision ae06c001a2546bef168b9bf8f570ccb1a16aaa27 --> |
|
- **Maximum Sequence Length:** 128 tokens |
|
- **Output Dimensionality:** 384 tokens |
|
- **Similarity Function:** Cosine Similarity |
|
- **Training Dataset:** |
|
- train |
|
- **Language:** hu |
|
- **License:** apache-2.0 |
|
|
|
### 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: BertModel |
|
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
) |
|
``` |
|
|
|
## 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("karsar/paraphrase-multilingual-MiniLM-L12-hu_v1") |
|
# Run inference |
|
sentences = [ |
|
'Az emberek alszanak.', |
|
'Egy apa és a fia ölelgeti alvás közben.', |
|
'Egy csoport ember ül egy nyitott, térszerű területen, mögötte nagy bokrok és egy sor viktoriánus stílusú épület, melyek közül sokat a kép jobb oldalán lévő erős elmosódás tesz kivehetetlenné.', |
|
] |
|
embeddings = model.encode(sentences) |
|
print(embeddings.shape) |
|
# [3, 384] |
|
|
|
# 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 |
|
|
|
#### Triplet |
|
* Dataset: `all-nli-dev` |
|
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) |
|
|
|
| Metric | Value | |
|
|:-------------------|:----------| |
|
| cosine_accuracy | 0.992 | |
|
| dot_accuracy | 0.0108 | |
|
| manhattan_accuracy | 0.9908 | |
|
| euclidean_accuracy | 0.9908 | |
|
| **max_accuracy** | **0.992** | |
|
|
|
#### Triplet |
|
* Dataset: `all-nli-test` |
|
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) |
|
|
|
| Metric | Value | |
|
|:-------------------|:-----------| |
|
| cosine_accuracy | 0.9914 | |
|
| dot_accuracy | 0.0139 | |
|
| manhattan_accuracy | 0.9909 | |
|
| euclidean_accuracy | 0.9911 | |
|
| **max_accuracy** | **0.9914** | |
|
|
|
<!-- |
|
## 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 |
|
|
|
#### train |
|
|
|
* Dataset: train |
|
* Size: 857,856 training samples |
|
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | anchor | positive | negative | |
|
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
|
| type | string | string | string | |
|
| details | <ul><li>min: 7 tokens</li><li>mean: 11.73 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.24 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.07 tokens</li><li>max: 53 tokens</li></ul> | |
|
* Samples: |
|
| anchor | positive | negative | |
|
|:---------------------------------------------------------------------------|:----------------------------------------------|:---------------------------------------------------------------| |
|
| <code>Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.</code> | <code>Egy ember a szabadban, lóháton.</code> | <code>Egy ember egy étteremben van, és omlettet rendel.</code> | |
|
| <code>Gyerekek mosolyogva és integetett a kamera</code> | <code>Gyermekek vannak jelen</code> | <code>A gyerekek homlokot rántanak</code> | |
|
| <code>Egy fiú ugrál a gördeszkát a közepén egy piros híd.</code> | <code>A fiú gördeszkás trükköt csinál.</code> | <code>A fiú korcsolyázik a járdán.</code> | |
|
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
|
```json |
|
{ |
|
"scale": 20.0, |
|
"similarity_fct": "cos_sim" |
|
} |
|
``` |
|
|
|
### Evaluation Dataset |
|
|
|
#### train |
|
|
|
* Dataset: train |
|
* Size: 5,000 evaluation samples |
|
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | anchor | positive | negative | |
|
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
|
| type | string | string | string | |
|
| details | <ul><li>min: 7 tokens</li><li>mean: 11.73 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.24 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.07 tokens</li><li>max: 53 tokens</li></ul> | |
|
* Samples: |
|
| anchor | positive | negative | |
|
|:---------------------------------------------------------------------------|:----------------------------------------------|:---------------------------------------------------------------| |
|
| <code>Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.</code> | <code>Egy ember a szabadban, lóháton.</code> | <code>Egy ember egy étteremben van, és omlettet rendel.</code> | |
|
| <code>Gyerekek mosolyogva és integetett a kamera</code> | <code>Gyermekek vannak jelen</code> | <code>A gyerekek homlokot rántanak</code> | |
|
| <code>Egy fiú ugrál a gördeszkát a közepén egy piros híd.</code> | <code>A fiú gördeszkás trükköt csinál.</code> | <code>A fiú korcsolyázik a járdán.</code> | |
|
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
|
```json |
|
{ |
|
"scale": 20.0, |
|
"similarity_fct": "cos_sim" |
|
} |
|
``` |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `eval_strategy`: steps |
|
- `per_device_train_batch_size`: 128 |
|
- `per_device_eval_batch_size`: 128 |
|
- `num_train_epochs`: 1 |
|
- `warmup_ratio`: 0.1 |
|
- `bf16`: True |
|
- `batch_sampler`: no_duplicates |
|
|
|
#### All Hyperparameters |
|
<details><summary>Click to expand</summary> |
|
|
|
- `overwrite_output_dir`: False |
|
- `do_predict`: False |
|
- `eval_strategy`: steps |
|
- `prediction_loss_only`: True |
|
- `per_device_train_batch_size`: 128 |
|
- `per_device_eval_batch_size`: 128 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 1 |
|
- `eval_accumulation_steps`: None |
|
- `torch_empty_cache_steps`: None |
|
- `learning_rate`: 5e-05 |
|
- `weight_decay`: 0.0 |
|
- `adam_beta1`: 0.9 |
|
- `adam_beta2`: 0.999 |
|
- `adam_epsilon`: 1e-08 |
|
- `max_grad_norm`: 1.0 |
|
- `num_train_epochs`: 1 |
|
- `max_steps`: -1 |
|
- `lr_scheduler_type`: linear |
|
- `lr_scheduler_kwargs`: {} |
|
- `warmup_ratio`: 0.1 |
|
- `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 |
|
- `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`: True |
|
- `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, '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`: 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_eval_metrics`: False |
|
- `eval_on_start`: False |
|
- `eval_use_gather_object`: False |
|
- `batch_sampler`: no_duplicates |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | train loss | all-nli-dev_max_accuracy | all-nli-test_max_accuracy | |
|
|:------:|:----:|:-------------:|:----------:|:------------------------:|:-------------------------:| |
|
| 0 | 0 | - | - | 0.7574 | - | |
|
| 0.0149 | 100 | 2.5002 | - | - | - | |
|
| 0.0298 | 200 | 1.9984 | - | - | - | |
|
| 0.0448 | 300 | 1.8094 | - | - | - | |
|
| 0.0597 | 400 | 1.6704 | - | - | - | |
|
| 0.0746 | 500 | 1.5518 | - | - | - | |
|
| 0.0895 | 600 | 1.449 | - | - | - | |
|
| 0.1044 | 700 | 1.5998 | - | - | - | |
|
| 0.1194 | 800 | 1.5725 | - | - | - | |
|
| 0.1343 | 900 | 1.5341 | - | - | - | |
|
| 0.1492 | 1000 | 1.3423 | - | - | - | |
|
| 0.1641 | 1100 | 1.2485 | - | - | - | |
|
| 0.1791 | 1200 | 1.1527 | - | - | - | |
|
| 0.1940 | 1300 | 1.1672 | - | - | - | |
|
| 0.2089 | 1400 | 1.2426 | - | - | - | |
|
| 0.2238 | 1500 | 1.0948 | - | - | - | |
|
| 0.2387 | 1600 | 1.0069 | - | - | - | |
|
| 0.2537 | 1700 | 0.976 | - | - | - | |
|
| 0.2686 | 1800 | 0.897 | - | - | - | |
|
| 0.2835 | 1900 | 0.7825 | - | - | - | |
|
| 0.2984 | 2000 | 0.9421 | 0.1899 | 0.9568 | - | |
|
| 0.3133 | 2100 | 0.8651 | - | - | - | |
|
| 0.3283 | 2200 | 0.8184 | - | - | - | |
|
| 0.3432 | 2300 | 0.699 | - | - | - | |
|
| 0.3581 | 2400 | 0.6704 | - | - | - | |
|
| 0.3730 | 2500 | 0.6477 | - | - | - | |
|
| 0.3879 | 2600 | 0.7077 | - | - | - | |
|
| 0.4029 | 2700 | 0.7364 | - | - | - | |
|
| 0.4178 | 2800 | 0.665 | - | - | - | |
|
| 0.4327 | 2900 | 1.2512 | - | - | - | |
|
| 0.4476 | 3000 | 1.3693 | - | - | - | |
|
| 0.4625 | 3100 | 1.3959 | - | - | - | |
|
| 0.4775 | 3200 | 1.4175 | - | - | - | |
|
| 0.4924 | 3300 | 1.402 | - | - | - | |
|
| 0.5073 | 3400 | 1.3832 | - | - | - | |
|
| 0.5222 | 3500 | 1.3671 | - | - | - | |
|
| 0.5372 | 3600 | 1.3666 | - | - | - | |
|
| 0.5521 | 3700 | 1.3479 | - | - | - | |
|
| 0.5670 | 3800 | 1.3272 | - | - | - | |
|
| 0.5819 | 3900 | 1.3353 | - | - | - | |
|
| 0.5968 | 4000 | 1.3177 | 0.0639 | 0.9902 | - | |
|
| 0.6118 | 4100 | 1.3068 | - | - | - | |
|
| 0.6267 | 4200 | 1.3054 | - | - | - | |
|
| 0.6416 | 4300 | 1.3098 | - | - | - | |
|
| 0.6565 | 4400 | 1.2839 | - | - | - | |
|
| 0.6714 | 4500 | 1.2976 | - | - | - | |
|
| 0.6864 | 4600 | 1.2669 | - | - | - | |
|
| 0.7013 | 4700 | 1.208 | - | - | - | |
|
| 0.7162 | 4800 | 1.194 | - | - | - | |
|
| 0.7311 | 4900 | 1.1974 | - | - | - | |
|
| 0.7460 | 5000 | 1.1834 | - | - | - | |
|
| 0.7610 | 5100 | 1.1876 | - | - | - | |
|
| 0.7759 | 5200 | 1.1743 | - | - | - | |
|
| 0.7908 | 5300 | 1.1839 | - | - | - | |
|
| 0.8057 | 5400 | 1.1778 | - | - | - | |
|
| 0.8207 | 5500 | 1.1711 | - | - | - | |
|
| 0.8356 | 5600 | 1.1809 | - | - | - | |
|
| 0.8505 | 5700 | 1.1825 | - | - | - | |
|
| 0.8654 | 5800 | 1.1795 | - | - | - | |
|
| 0.8803 | 5900 | 1.1788 | - | - | - | |
|
| 0.8953 | 6000 | 1.1819 | 0.0371 | 0.992 | - | |
|
| 0.9102 | 6100 | 1.1741 | - | - | - | |
|
| 0.9251 | 6200 | 1.1871 | - | - | - | |
|
| 0.9400 | 6300 | 0.498 | - | - | - | |
|
| 0.9549 | 6400 | 0.093 | - | - | - | |
|
| 0.9699 | 6500 | 0.1597 | - | - | - | |
|
| 0.9848 | 6600 | 0.2033 | - | - | - | |
|
| 0.9997 | 6700 | 0.16 | - | - | - | |
|
| 1.0 | 6702 | - | - | - | 0.9914 | |
|
|
|
|
|
### Framework Versions |
|
- Python: 3.11.8 |
|
- Sentence Transformers: 3.1.1 |
|
- Transformers: 4.44.0 |
|
- PyTorch: 2.3.0.post101 |
|
- Accelerate: 0.33.0 |
|
- Datasets: 2.18.0 |
|
- Tokenizers: 0.19.0 |
|
|
|
## 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", |
|
} |
|
``` |
|
|
|
#### MultipleNegativesRankingLoss |
|
```bibtex |
|
@misc{henderson2017efficient, |
|
title={Efficient Natural Language Response Suggestion for Smart Reply}, |
|
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, |
|
year={2017}, |
|
eprint={1705.00652}, |
|
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.* |
|
--> |
|
--- |
