diff --git "a/README.md" "b/README.md" --- "a/README.md" +++ "b/README.md" @@ -3,7 +3,7 @@ license: cc-by-nc-4.0 tags: - mteb model-index: -- name: text_sonar_basic_encoder +- name: text_sonar_basic_encoder_normalized results: - task: type: Clustering @@ -15,7 +15,7 @@ model-index: revision: None metrics: - type: v_measure - value: 14.51482032569021 + value: 18.787544117314575 - task: type: STS dataset: @@ -26,17 +26,17 @@ model-index: revision: b44c3b011063adb25877c13823db83bb193913c4 metrics: - type: cos_sim_pearson - value: 17.970264353352682 + value: 17.97026675319667 - type: cos_sim_spearman - value: 17.633997882973155 + value: 17.63407829948615 - type: euclidean_pearson - value: 14.014776236053123 + value: 17.704571608660725 - type: euclidean_spearman - value: 15.28941515698961 + value: 17.634078298828143 - type: manhattan_pearson - value: 13.891563198299256 + value: 17.606959101509464 - type: manhattan_spearman - value: 15.158415586569143 + value: 17.549620164990085 - task: type: STS dataset: @@ -47,17 +47,17 @@ model-index: revision: 0f319b1142f28d00e055a6770f3f726ae9b7d865 metrics: - type: cos_sim_pearson - value: 27.670887710562912 + value: 27.670887504789675 - type: cos_sim_spearman - value: 26.176635036642804 + value: 26.176629407301782 - type: euclidean_pearson - value: 24.115430353423346 + value: 28.878485717935586 - type: euclidean_spearman - value: 24.31920807107195 + value: 26.176635036613355 - type: manhattan_pearson - value: 23.998151286247396 + value: 28.782373978690103 - type: manhattan_spearman - value: 24.167187716649224 + value: 26.055266444113794 - task: type: Classification dataset: @@ -68,9 +68,9 @@ model-index: revision: None metrics: - type: accuracy - value: 29.85089463220676 + value: 29.62226640159046 - type: f1 - value: 27.632986641843516 + value: 27.632722290701047 - task: type: Classification dataset: @@ -81,11 +81,11 @@ model-index: revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy - value: 78.98507462686568 + value: 81.49253731343285 - type: ap - value: 44.08138737273602 + value: 46.61440947240349 - type: f1 - value: 73.46285533200773 + value: 75.68925212232107 - task: type: Classification dataset: @@ -96,11 +96,11 @@ model-index: revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy - value: 72.00214132762312 + value: 72.02355460385438 - type: ap - value: 82.19993680100252 + value: 83.13664983282676 - type: f1 - value: 70.11447824125146 + value: 70.48997817871013 - task: type: Classification dataset: @@ -111,11 +111,11 @@ model-index: revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy - value: 81.28935532233884 + value: 82.09145427286357 - type: ap - value: 30.144590364670528 + value: 31.45181004731995 - type: f1 - value: 68.42566054607258 + value: 69.41750580313406 - task: type: Classification dataset: @@ -126,11 +126,11 @@ model-index: revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy - value: 67.7730192719486 + value: 71.78800856531049 - type: ap - value: 18.42471917082788 + value: 19.65443896353892 - type: f1 - value: 55.72761001975526 + value: 58.436688187826334 - task: type: Classification dataset: @@ -141,11 +141,11 @@ model-index: revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy - value: 61.521125 + value: 62.73074999999999 - type: ap - value: 57.23445163027374 + value: 58.2839375458089 - type: f1 - value: 60.73008406893218 + value: 62.16204082406629 - task: type: Classification dataset: @@ -156,9 +156,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 30.491999999999997 + value: 31.552000000000003 - type: f1 - value: 29.557204623883994 + value: 31.125328770568277 - task: type: Classification dataset: @@ -169,9 +169,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 33.386 + value: 34.611999999999995 - type: f1 - value: 31.84048812033152 + value: 33.93738697105999 - task: type: Classification dataset: @@ -182,9 +182,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 34.866 + value: 35.172 - type: f1 - value: 32.99012859140412 + value: 34.14112656493798 - task: type: Classification dataset: @@ -195,9 +195,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 34.062000000000005 + value: 34.910000000000004 - type: f1 - value: 33.25848878845983 + value: 34.276631172288965 - task: type: Classification dataset: @@ -208,9 +208,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 31.023999999999997 + value: 31.844 - type: f1 - value: 30.458831589997278 + value: 31.478780923476368 - task: type: Classification dataset: @@ -221,9 +221,9 @@ model-index: revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy - value: 30.994 + value: 31.912000000000003 - type: f1 - value: 30.061575356482727 + value: 31.384992191831312 - task: type: Classification dataset: @@ -234,9 +234,9 @@ model-index: revision: 20b0e6081892e78179356fada741b7afa381443d metrics: - type: accuracy - value: 48.223495702005735 + value: 49.61795606494747 - type: f1 - value: 47.162760921004896 + value: 48.63625944670304 - task: type: Retrieval dataset: @@ -306,6 +306,75 @@ model-index: value: 17.354 - type: recall_at_5 value: 22.902 + - task: + type: Retrieval + dataset: + type: arguana-pl + name: MTEB ArguAna-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 7.752000000000001 + - type: map_at_10 + value: 12.248000000000001 + - type: map_at_100 + value: 12.882 + - type: map_at_1000 + value: 12.963 + - type: map_at_3 + value: 10.574 + - type: map_at_5 + value: 11.566 + - type: mrr_at_1 + value: 7.824000000000001 + - type: mrr_at_10 + value: 12.293 + - type: mrr_at_100 + value: 12.928 + - type: mrr_at_1000 + value: 13.008000000000001 + - type: mrr_at_3 + value: 10.586 + - type: mrr_at_5 + value: 11.599 + - type: ndcg_at_1 + value: 7.752000000000001 + - type: ndcg_at_10 + value: 15.035000000000002 + - type: ndcg_at_100 + value: 18.497 + - type: ndcg_at_1000 + value: 20.896 + - type: ndcg_at_3 + value: 11.578 + - type: ndcg_at_5 + value: 13.38 + - type: precision_at_1 + value: 7.752000000000001 + - type: precision_at_10 + value: 2.404 + - type: precision_at_100 + value: 0.411 + - type: precision_at_1000 + value: 0.061 + - type: precision_at_3 + value: 4.836 + - type: precision_at_5 + value: 3.784 + - type: recall_at_1 + value: 7.752000000000001 + - type: recall_at_10 + value: 24.04 + - type: recall_at_100 + value: 41.11 + - type: recall_at_1000 + value: 60.597 + - type: recall_at_3 + value: 14.509 + - type: recall_at_5 + value: 18.919 - task: type: Clustering dataset: @@ -316,7 +385,7 @@ model-index: revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure - value: 25.78534535464707 + value: 26.81177290816682 - task: type: Clustering dataset: @@ -327,7 +396,7 @@ model-index: revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure - value: 22.935310338963955 + value: 24.346811178757022 - task: type: Reranking dataset: @@ -351,17 +420,17 @@ model-index: revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson - value: 77.15058570798328 + value: 77.15058512395619 - type: cos_sim_spearman value: 79.10541692841936 - type: euclidean_pearson - value: 57.77256072255626 + value: 75.30525535929353 - type: euclidean_spearman - value: 61.9206880133157 + value: 79.10541692841936 - type: manhattan_pearson - value: 57.61971995547671 + value: 75.33508042552984 - type: manhattan_spearman - value: 61.65983869619309 + value: 78.84577245802708 - task: type: STS dataset: @@ -372,17 +441,17 @@ model-index: revision: e3dda5e115e487b39ec7e618c0c6a29137052a55 metrics: - type: cos_sim_pearson - value: 37.84739182483413 + value: 37.84739189558895 - type: cos_sim_spearman - value: 37.6627002178424 + value: 37.662710610486265 - type: euclidean_pearson - value: 31.20207774134489 + value: 37.5407537185213 - type: euclidean_spearman - value: 32.258185520047554 + value: 37.66272446700578 - type: manhattan_pearson - value: 31.45043795745484 + value: 37.863820146709706 - type: manhattan_spearman - value: 32.432706960003095 + value: 38.09120266204032 - task: type: BitextMining dataset: @@ -461,9 +530,9 @@ model-index: revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy - value: 70.12012987012987 + value: 73.49675324675324 - type: f1 - value: 69.2899512261214 + value: 72.88538992490979 - task: type: Clustering dataset: @@ -474,7 +543,7 @@ model-index: revision: 62d5330920bca426ce9d3c76ea914f15fc83e891 metrics: - type: v_measure - value: 7.691890146277049 + value: 6.801245618724224 - task: type: Clustering dataset: @@ -485,7 +554,7 @@ model-index: revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure - value: 18.50684170881271 + value: 20.6156033971932 - task: type: Clustering dataset: @@ -496,7 +565,7 @@ model-index: revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure - value: 16.69474554114157 + value: 19.077587707743156 - task: type: Clustering dataset: @@ -507,7 +576,7 @@ model-index: revision: a2dd5b02a77de3466a3eaa98ae586b5610314496 metrics: - type: v_measure - value: 25.00467105836009 + value: 27.00349462858046 - task: type: Clustering dataset: @@ -518,7 +587,7 @@ model-index: revision: 9bfff9a7f8f6dc6ffc9da71c48dd48b68696471d metrics: - type: v_measure - value: 13.043482009500194 + value: 14.845348131791589 - task: type: BitextMining dataset: @@ -531,9 +600,9 @@ model-index: - type: accuracy value: 54.0 - type: f1 - value: 47.33693528693529 + value: 47.37026862026861 - type: precision - value: 45.04007936507936 + value: 45.0734126984127 - type: recall value: 54.0 - task: @@ -546,11 +615,11 @@ model-index: revision: None metrics: - type: accuracy - value: 66.62 + value: 63.83000000000001 - type: ap - value: 18.77536577595191 + value: 18.511972946438764 - type: f1 - value: 54.33122331135114 + value: 53.16787370496645 - task: type: PairClassification dataset: @@ -571,41 +640,41 @@ model-index: - type: cos_sim_recall value: 79.47368421052632 - type: dot_accuracy - value: 83.7 + value: 84.39999999999999 - type: dot_ap - value: 51.707245136367455 + value: 59.968589741258036 - type: dot_f1 - value: 52.03619909502262 + value: 54.90909090909091 - type: dot_precision - value: 45.63492063492063 + value: 41.94444444444444 - type: dot_recall - value: 60.526315789473685 + value: 79.47368421052632 - type: euclidean_accuracy - value: 84.3 + value: 84.39999999999999 - type: euclidean_ap - value: 60.640177471697974 + value: 59.968589741258036 - type: euclidean_f1 - value: 56.55737704918033 + value: 54.90909090909091 - type: euclidean_precision - value: 46.308724832214764 + value: 41.94444444444444 - type: euclidean_recall - value: 72.63157894736842 + value: 79.47368421052632 - type: manhattan_accuracy - value: 84.3 + value: 84.39999999999999 - type: manhattan_ap - value: 60.642449283992626 + value: 60.094893481041154 - type: manhattan_f1 - value: 56.82242990654205 + value: 55.452865064695004 - type: manhattan_precision - value: 44.05797101449275 + value: 42.73504273504273 - type: manhattan_recall - value: 80.0 + value: 78.94736842105263 - type: max_accuracy value: 84.39999999999999 - type: max_ap - value: 60.642449283992626 + value: 60.094893481041154 - type: max_f1 - value: 56.82242990654205 + value: 55.452865064695004 - task: type: STS dataset: @@ -616,17 +685,17 @@ model-index: revision: None metrics: - type: cos_sim_pearson - value: 83.84274209712814 + value: 83.8427417206754 - type: cos_sim_spearman - value: 85.76929022706523 + value: 85.76946319798301 - type: euclidean_pearson - value: 79.29678840568863 + value: 79.43901249477852 - type: euclidean_spearman - value: 83.83915785622271 + value: 85.76946319798301 - type: manhattan_pearson - value: 79.51377951133192 + value: 79.81046681362531 - type: manhattan_spearman - value: 84.01330353535174 + value: 86.24115514951988 - task: type: Clustering dataset: @@ -637,7 +706,7 @@ model-index: revision: 4b6227591c6c1a73bc76b1055f3b7f3588e72476 metrics: - type: v_measure - value: 26.145917838254785 + value: 27.432031859995952 - task: type: Clustering dataset: @@ -648,7 +717,7 @@ model-index: revision: e458b3f5414b62b7f9f83499ac1f5497ae2e869f metrics: - type: v_measure - value: 28.0310744137802 + value: 28.32367305628197 - task: type: Reranking dataset: @@ -659,9 +728,9 @@ model-index: revision: 8d7f1e942507dac42dc58017c1a001c3717da7df metrics: - type: map - value: 34.30811576227924 + value: 34.30720667137015 - type: mrr - value: 40.25416666666666 + value: 40.24416666666666 - task: type: Reranking dataset: @@ -1722,7 +1791,7 @@ model-index: - type: cos_sim_accuracy value: 58.123872519543 - type: cos_sim_ap - value: 61.860457891021845 + value: 61.86046509726734 - type: cos_sim_f1 value: 68.18181818181817 - type: cos_sim_precision @@ -1730,41 +1799,41 @@ model-index: - type: cos_sim_recall value: 97.49824643441664 - type: dot_accuracy - value: 59.02585688514732 + value: 58.123872519543 - type: dot_ap - value: 62.10634470973564 + value: 61.860555259802986 - type: dot_f1 - value: 68.3513630463003 + value: 68.18181818181817 - type: dot_precision - value: 54.259411926353394 + value: 52.4198617221873 - type: dot_recall - value: 92.33107318213702 + value: 97.49824643441664 - type: euclidean_accuracy - value: 54.696331930246544 + value: 58.123872519543 - type: euclidean_ap - value: 59.58239795823632 + value: 61.87698627731538 - type: euclidean_f1 - value: 67.95360660946935 + value: 68.18181818181817 - type: euclidean_precision - value: 51.46191794007942 + value: 52.4198617221873 - type: euclidean_recall - value: 100.0 + value: 97.49824643441664 - type: manhattan_accuracy - value: 54.696331930246544 + value: 58.123872519543 - type: manhattan_ap - value: 59.593398063507394 + value: 61.99468883207791 - type: manhattan_f1 - value: 67.94311591324383 + value: 68.33675564681727 - type: manhattan_precision - value: 51.4560770156438 + value: 52.671562420866046 - type: manhattan_recall - value: 99.9766191255553 + value: 97.26443768996961 - type: max_accuracy - value: 59.02585688514732 + value: 58.123872519543 - type: max_ap - value: 62.10634470973564 + value: 61.99468883207791 - type: max_f1 - value: 68.3513630463003 + value: 68.33675564681727 - task: type: Retrieval dataset: @@ -1781,7 +1850,7 @@ model-index: - type: map_at_100 value: 9.549000000000001 - type: map_at_1000 - value: 9.666 + value: 9.665 - type: map_at_3 value: 8.061 - type: map_at_5 @@ -1803,9 +1872,9 @@ model-index: - type: ndcg_at_10 value: 10.382 - type: ndcg_at_100 - value: 14.237 + value: 14.235999999999999 - type: ndcg_at_1000 - value: 18.041 + value: 18.04 - type: ndcg_at_3 value: 8.613999999999999 - type: ndcg_at_5 @@ -1913,11 +1982,11 @@ model-index: revision: 59d12749a3c91a186063c7d729ec392fda94681c metrics: - type: accuracy - value: 70.42553191489363 + value: 69.96960486322187 - type: ap - value: 90.43423476644443 + value: 91.23131906690253 - type: f1 - value: 55.82951993211343 + value: 57.11872970138122 - task: type: Classification dataset: @@ -1928,11 +1997,11 @@ model-index: revision: 7ebf0b4caa7b2ae39698a889de782c09e6f5ee56 metrics: - type: accuracy - value: 50.04504504504504 + value: 49.75225225225225 - type: ap - value: 50.02574261238442 + value: 49.88223192425368 - type: f1 - value: 49.48578760810561 + value: 49.55059044107012 - task: type: Classification dataset: @@ -1943,9 +2012,9 @@ model-index: revision: edbb03726c04a0efab14fc8c3b8b79e4d420e5a1 metrics: - type: accuracy - value: 34.26450180405217 + value: 37.58534554537886 - type: f1 - value: 30.14302584747605 + value: 33.99440115952713 - task: type: Retrieval dataset: @@ -2094,9 +2163,9 @@ model-index: revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy - value: 36.52 + value: 38.285000000000004 - type: f1 - value: 33.66164203159101 + value: 35.35979931355028 - task: type: Retrieval dataset: @@ -2166,6 +2235,75 @@ model-index: value: 1.4200000000000002 - type: recall_at_5 value: 1.81 + - task: + type: Retrieval + dataset: + type: fiqa-pl + name: MTEB FiQA-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 0.959 + - type: map_at_10 + value: 1.952 + - type: map_at_100 + value: 2.281 + - type: map_at_1000 + value: 2.393 + - type: map_at_3 + value: 1.703 + - type: map_at_5 + value: 1.8319999999999999 + - type: mrr_at_1 + value: 2.469 + - type: mrr_at_10 + value: 4.547 + - type: mrr_at_100 + value: 5.021 + - type: mrr_at_1000 + value: 5.1339999999999995 + - type: mrr_at_3 + value: 3.884 + - type: mrr_at_5 + value: 4.223 + - type: ndcg_at_1 + value: 2.469 + - type: ndcg_at_10 + value: 3.098 + - type: ndcg_at_100 + value: 5.177 + - type: ndcg_at_1000 + value: 8.889 + - type: ndcg_at_3 + value: 2.7119999999999997 + - type: ndcg_at_5 + value: 2.8000000000000003 + - type: precision_at_1 + value: 2.469 + - type: precision_at_10 + value: 1.065 + - type: precision_at_100 + value: 0.321 + - type: precision_at_1000 + value: 0.095 + - type: precision_at_3 + value: 2.109 + - type: precision_at_5 + value: 1.574 + - type: recall_at_1 + value: 0.959 + - type: recall_at_10 + value: 4.075 + - type: recall_at_100 + value: 12.487 + - type: recall_at_1000 + value: 36.854 + - type: recall_at_3 + value: 2.632 + - type: recall_at_5 + value: 3.231 - task: type: Retrieval dataset: @@ -2235,6 +2373,144 @@ model-index: value: 2.37 - type: recall_at_5 value: 3.077 + - task: + type: Retrieval + dataset: + type: jinaai/ger_da_lir + name: MTEB GerDaLIR + config: default + split: test + revision: 0bb47f1d73827e96964edb84dfe552f62f4fd5eb + metrics: + - type: map_at_1 + value: 0.542 + - type: map_at_10 + value: 0.8130000000000001 + - type: map_at_100 + value: 0.898 + - type: map_at_1000 + value: 0.9209999999999999 + - type: map_at_3 + value: 0.709 + - type: map_at_5 + value: 0.764 + - type: mrr_at_1 + value: 0.594 + - type: mrr_at_10 + value: 0.8880000000000001 + - type: mrr_at_100 + value: 0.9820000000000001 + - type: mrr_at_1000 + value: 1.008 + - type: mrr_at_3 + value: 0.774 + - type: mrr_at_5 + value: 0.832 + - type: ndcg_at_1 + value: 0.594 + - type: ndcg_at_10 + value: 1.0030000000000001 + - type: ndcg_at_100 + value: 1.537 + - type: ndcg_at_1000 + value: 2.4330000000000003 + - type: ndcg_at_3 + value: 0.782 + - type: ndcg_at_5 + value: 0.882 + - type: precision_at_1 + value: 0.594 + - type: precision_at_10 + value: 0.16999999999999998 + - type: precision_at_100 + value: 0.048 + - type: precision_at_1000 + value: 0.013 + - type: precision_at_3 + value: 0.33899999999999997 + - type: precision_at_5 + value: 0.255 + - type: recall_at_1 + value: 0.542 + - type: recall_at_10 + value: 1.533 + - type: recall_at_100 + value: 4.204 + - type: recall_at_1000 + value: 11.574 + - type: recall_at_3 + value: 0.932 + - type: recall_at_5 + value: 1.172 + - task: + type: Retrieval + dataset: + type: deepset/germandpr + name: MTEB GermanDPR + config: default + split: test + revision: 5129d02422a66be600ac89cd3e8531b4f97d347d + metrics: + - type: map_at_1 + value: 25.561 + - type: map_at_10 + value: 38.873000000000005 + - type: map_at_100 + value: 40.004 + - type: map_at_1000 + value: 40.03 + - type: map_at_3 + value: 34.585 + - type: map_at_5 + value: 36.980000000000004 + - type: mrr_at_1 + value: 25.463 + - type: mrr_at_10 + value: 38.792 + - type: mrr_at_100 + value: 39.922000000000004 + - type: mrr_at_1000 + value: 39.949 + - type: mrr_at_3 + value: 34.504000000000005 + - type: mrr_at_5 + value: 36.899 + - type: ndcg_at_1 + value: 25.561 + - type: ndcg_at_10 + value: 46.477000000000004 + - type: ndcg_at_100 + value: 51.751999999999995 + - type: ndcg_at_1000 + value: 52.366 + - type: ndcg_at_3 + value: 37.645 + - type: ndcg_at_5 + value: 41.953 + - type: precision_at_1 + value: 25.561 + - type: precision_at_10 + value: 7.083 + - type: precision_at_100 + value: 0.9490000000000001 + - type: precision_at_1000 + value: 0.1 + - type: precision_at_3 + value: 15.512 + - type: precision_at_5 + value: 11.395 + - type: recall_at_1 + value: 25.561 + - type: recall_at_10 + value: 70.829 + - type: recall_at_100 + value: 94.92699999999999 + - type: recall_at_1000 + value: 99.61 + - type: recall_at_3 + value: 46.537 + - type: recall_at_5 + value: 56.976000000000006 - task: type: Retrieval dataset: @@ -2304,6 +2580,27 @@ model-index: value: 74.002 - type: recall_at_5 value: 81.443 + - task: + type: STS + dataset: + type: jinaai/german-STSbenchmark + name: MTEB GermanSTSBenchmark + config: default + split: test + revision: e36907544d44c3a247898ed81540310442329e20 + metrics: + - type: cos_sim_pearson + value: 68.82052535790737 + - type: cos_sim_spearman + value: 67.9356892072251 + - type: euclidean_pearson + value: 67.2308663006278 + - type: euclidean_spearman + value: 67.93572522920142 + - type: manhattan_pearson + value: 67.23568952733595 + - type: manhattan_spearman + value: 67.91660489262797 - task: type: Retrieval dataset: @@ -2383,9 +2680,9 @@ model-index: revision: 421605374b29664c5fc098418fe20ada9bd55f8a metrics: - type: accuracy - value: 30.157752981916126 + value: 38.01462100808003 - type: f1 - value: 18.801823560719093 + value: 26.680357453754215 - task: type: Classification dataset: @@ -2396,11 +2693,11 @@ model-index: revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy - value: 55.2292 + value: 55.7508 - type: ap - value: 53.00916532305935 + value: 53.28158993124153 - type: f1 - value: 54.6906813069184 + value: 55.34571379744637 - task: type: Classification dataset: @@ -2411,11 +2708,11 @@ model-index: revision: b7c64bd89eb87f8ded463478346f76731f07bf8b metrics: - type: accuracy - value: 66.73545966228893 + value: 69.58724202626641 - type: ap - value: 26.119597600779542 + value: 30.04577466931377 - type: f1 - value: 58.52011222432435 + value: 62.46921898313143 - task: type: STS dataset: @@ -2426,17 +2723,17 @@ model-index: revision: 17f9b096f80380fce5ed12a9be8be7784b337daf metrics: - type: cos_sim_pearson - value: 48.805858778250645 + value: 48.80585861169271 - type: cos_sim_spearman - value: 50.1102532604773 + value: 50.11025991147549 - type: euclidean_pearson - value: 48.94915568787808 + value: 50.055425341198934 - type: euclidean_spearman - value: 49.20965979933496 + value: 50.11024862622995 - type: manhattan_pearson - value: 48.913528193330855 + value: 50.029980024931064 - type: manhattan_spearman - value: 49.151438504736994 + value: 50.074388245963384 - task: type: Classification dataset: @@ -2447,9 +2744,22 @@ model-index: revision: de7ba3406ee55ea2cc52a0a41408fa6aede6d3c6 metrics: - type: accuracy - value: 53.13333333333333 + value: 54.266666666666666 - type: f1 - value: 51.09906324617105 + value: 52.181931818742875 + - task: + type: Reranking + dataset: + type: jinaai/miracl + name: MTEB MIRACL + config: default + split: test + revision: d28a029f35c4ff7f616df47b0edf54e6882395e6 + metrics: + - type: map + value: 51.40745004398599 + - type: mrr + value: 56.71940267335004 - task: type: Reranking dataset: @@ -2611,9 +2921,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 88.25809393524851 + value: 89.92476060191518 - type: f1 - value: 87.67467702138386 + value: 89.30222882069823 - task: type: Classification dataset: @@ -2624,9 +2934,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 87.86136939983095 + value: 89.54353338968724 - type: f1 - value: 86.46545913246018 + value: 88.23043644828002 - task: type: Classification dataset: @@ -2637,9 +2947,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 88.66911274182789 + value: 90.62374916611076 - type: f1 - value: 87.56818480133035 + value: 89.68544977510335 - task: type: Classification dataset: @@ -2650,9 +2960,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 82.32070153460695 + value: 86.18540557469466 - type: f1 - value: 81.8684135195111 + value: 85.7362674669331 - task: type: Classification dataset: @@ -2663,9 +2973,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 88.17497310864108 + value: 89.41556113302258 - type: f1 - value: 87.77127061255791 + value: 89.04934651990581 - task: type: Classification dataset: @@ -2676,9 +2986,9 @@ model-index: revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy - value: 83.61301989150091 + value: 85.89511754068715 - type: f1 - value: 83.32707952781637 + value: 85.57630467968119 - task: type: Classification dataset: @@ -2689,9 +2999,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 63.28545371637026 + value: 70.85043319653442 - type: f1 - value: 39.28010634448113 + value: 46.0794069318026 - task: type: Classification dataset: @@ -2702,9 +3012,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 67.51197520428289 + value: 73.43195266272188 - type: f1 - value: 42.75299728819045 + value: 48.08015719781981 - task: type: Classification dataset: @@ -2715,9 +3025,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 66.75783855903936 + value: 73.8425617078052 - type: f1 - value: 41.9243384646481 + value: 49.37915156189611 - task: type: Classification dataset: @@ -2728,9 +3038,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 57.61352959599124 + value: 66.75227059191982 - type: f1 - value: 36.60494253557738 + value: 43.4642946741452 - task: type: Classification dataset: @@ -2741,9 +3051,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 63.209035496593756 + value: 69.13589100035855 - type: f1 - value: 38.34334001455857 + value: 46.25935961966482 - task: type: Classification dataset: @@ -2754,9 +3064,9 @@ model-index: revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy - value: 62.01084990958409 + value: 68.47016274864377 - type: f1 - value: 38.90143964367107 + value: 46.197113305277796 - task: type: Classification dataset: @@ -2767,9 +3077,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 53.48016139878952 + value: 58.14727639542704 - type: f1 - value: 51.413731172932984 + value: 55.58745169431752 - task: type: Classification dataset: @@ -2780,9 +3090,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 52.74041694687289 + value: 57.91190316072628 - type: f1 - value: 50.85469558689613 + value: 55.46589962622107 - task: type: Classification dataset: @@ -2793,9 +3103,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 52.42098184263618 + value: 57.22932078009414 - type: f1 - value: 49.036138779692024 + value: 53.661218041561334 - task: type: Classification dataset: @@ -2806,9 +3116,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 51.72158708809683 + value: 57.16543375924681 - type: f1 - value: 50.92312837840828 + value: 55.16504653263189 - task: type: Classification dataset: @@ -2819,9 +3129,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.71015467383995 + value: 62.239408204438476 - type: f1 - value: 54.43623536118849 + value: 58.941991707183874 - task: type: Classification dataset: @@ -2832,9 +3142,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 44.86886348352387 + value: 51.186953597848 - type: f1 - value: 45.25621242204162 + value: 49.59432722397084 - task: type: Classification dataset: @@ -2845,9 +3155,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.554808338937455 + value: 62.030934767989244 - type: f1 - value: 52.841205727784924 + value: 58.836302050830966 - task: type: Classification dataset: @@ -2858,9 +3168,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.94149293880296 + value: 61.314727639542696 - type: f1 - value: 52.93531236014481 + value: 57.80700293522655 - task: type: Classification dataset: @@ -2871,9 +3181,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.95090786819098 + value: 64.20645595158037 - type: f1 - value: 55.8924018128682 + value: 61.36755812840151 - task: type: Classification dataset: @@ -2884,9 +3194,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.871553463349024 + value: 64.36785474108943 - type: f1 - value: 55.48077228016125 + value: 61.15645935863754 - task: type: Classification dataset: @@ -2897,9 +3207,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 59.05514458641561 + value: 63.97108271687962 - type: f1 - value: 56.85428621465761 + value: 62.07352472659557 - task: type: Classification dataset: @@ -2910,9 +3220,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 62.51849361129792 + value: 66.67114996637525 - type: f1 - value: 59.20555321128111 + value: 63.420170447126324 - task: type: Classification dataset: @@ -2923,9 +3233,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.13718897108272 + value: 62.864828513786144 - type: f1 - value: 55.11327164614034 + value: 59.655860488861926 - task: type: Classification dataset: @@ -2936,9 +3246,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 51.3046402151984 + value: 58.55077336919974 - type: f1 - value: 49.54359751420772 + value: 55.28215385204243 - task: type: Classification dataset: @@ -2949,9 +3259,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 59.512441156691324 + value: 63.453261600538 - type: f1 - value: 55.70948727453885 + value: 59.991998820039186 - task: type: Classification dataset: @@ -2962,9 +3272,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.69266980497647 + value: 61.32145258910558 - type: f1 - value: 53.84873884279824 + value: 58.9676667104426 - task: type: Classification dataset: @@ -2975,9 +3285,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.821116341627445 + value: 62.905178211163424 - type: f1 - value: 54.58226169327551 + value: 59.645126480791674 - task: type: Classification dataset: @@ -2988,9 +3298,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.282447881640884 + value: 60.03026227303295 - type: f1 - value: 52.46174777918203 + value: 56.68905593909442 - task: type: Classification dataset: @@ -3001,9 +3311,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.49697377269669 + value: 63.28850033624749 - type: f1 - value: 55.47458535278922 + value: 60.21862015326403 - task: type: Classification dataset: @@ -3014,9 +3324,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 50.931405514458625 + value: 56.0221923335575 - type: f1 - value: 48.76072294143928 + value: 53.388473451598315 - task: type: Classification dataset: @@ -3027,9 +3337,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.920645595158035 + value: 64.44182918628111 - type: f1 - value: 56.737389242501735 + value: 62.14806714489123 - task: type: Classification dataset: @@ -3040,9 +3350,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.890383322125096 + value: 63.69535978480162 - type: f1 - value: 57.204112622120874 + value: 62.40231098840202 - task: type: Classification dataset: @@ -3053,9 +3363,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 47.74714189643577 + value: 52.00067249495628 - type: f1 - value: 45.39014412767061 + value: 48.871263427511984 - task: type: Classification dataset: @@ -3066,9 +3376,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 49.91930060524547 + value: 54.088769334229994 - type: f1 - value: 48.95180513332781 + value: 52.68998451556 - task: type: Classification dataset: @@ -3079,9 +3389,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 37.989240080699396 + value: 43.34229993275051 - type: f1 - value: 36.10638372264491 + value: 40.578510490463024 - task: type: Classification dataset: @@ -3092,9 +3402,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 53.2985877605918 + value: 57.87491593813046 - type: f1 - value: 51.12206506352444 + value: 55.19579071673386 - task: type: Classification dataset: @@ -3105,9 +3415,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.12373907195696 + value: 62.69334229993275 - type: f1 - value: 56.204584512225274 + value: 60.90210922623679 - task: type: Classification dataset: @@ -3118,9 +3428,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 50.11768661735038 + value: 56.240753194351036 - type: f1 - value: 48.593654115832884 + value: 54.137519761157485 - task: type: Classification dataset: @@ -3131,9 +3441,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.91862811028917 + value: 62.81439139206457 - type: f1 - value: 55.78809760336119 + value: 60.46554841337619 - task: type: Classification dataset: @@ -3144,9 +3454,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 53.47679892400807 + value: 58.49361129791527 - type: f1 - value: 50.59933850617468 + value: 55.12919894175168 - task: type: Classification dataset: @@ -3157,9 +3467,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 56.32145258910557 + value: 61.55682582380633 - type: f1 - value: 53.78572864251967 + value: 58.81763499302702 - task: type: Classification dataset: @@ -3170,9 +3480,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 53.544048419636844 + value: 59.3981170141224 - type: f1 - value: 50.74399745452213 + value: 56.31810441546048 - task: type: Classification dataset: @@ -3183,9 +3493,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.05716207128446 + value: 59.89576328177538 - type: f1 - value: 53.12820524166937 + value: 57.35130066022407 - task: type: Classification dataset: @@ -3196,9 +3506,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 59.37794216543376 + value: 64.55951580363148 - type: f1 - value: 56.614794144008386 + value: 61.50868742463585 - task: type: Classification dataset: @@ -3209,9 +3519,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 60.813718897108274 + value: 65.86079354404842 - type: f1 - value: 57.15694453759643 + value: 61.94702597578807 - task: type: Classification dataset: @@ -3222,9 +3532,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.399462004034966 + value: 63.49024882313383 - type: f1 - value: 55.93483217710289 + value: 60.796412851533454 - task: type: Classification dataset: @@ -3235,9 +3545,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.763954270342964 + value: 62.53194351042366 - type: f1 - value: 55.09638860069861 + value: 59.9167382336848 - task: type: Classification dataset: @@ -3248,9 +3558,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.65232010759921 + value: 62.62945527908541 - type: f1 - value: 52.30181938086533 + value: 59.195444230665096 - task: type: Classification dataset: @@ -3261,9 +3571,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 58.74915938130465 + value: 63.43308675184935 - type: f1 - value: 55.4593730920787 + value: 60.605749901316145 - task: type: Classification dataset: @@ -3274,9 +3584,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 56.90316072629456 + value: 61.44586415601883 - type: f1 - value: 54.28504920273749 + value: 58.635066561729396 - task: type: Classification dataset: @@ -3287,9 +3597,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.52185608607936 + value: 62.86482851378615 - type: f1 - value: 54.65171004538219 + value: 59.75440194153033 - task: type: Classification dataset: @@ -3300,9 +3610,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 50.47074646940148 + value: 56.250840618695364 - type: f1 - value: 49.91640094830554 + value: 54.84944007944625 - task: type: Classification dataset: @@ -3313,9 +3623,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 54.482178883658364 + value: 59.747814391392076 - type: f1 - value: 52.24226771901219 + value: 56.83761137925043 - task: type: Classification dataset: @@ -3326,9 +3636,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 54.64357767316746 + value: 59.60995292535306 - type: f1 - value: 53.01487636439553 + value: 57.106776457430705 - task: type: Classification dataset: @@ -3339,9 +3649,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 54.115669132481514 + value: 59.421654337592464 - type: f1 - value: 52.413205142753206 + value: 57.81013790437749 - task: type: Classification dataset: @@ -3352,9 +3662,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 52.95225285810356 + value: 58.120376597175515 - type: f1 - value: 50.75756649910168 + value: 55.27690756097837 - task: type: Classification dataset: @@ -3365,9 +3675,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 51.66778749159382 + value: 60.907868190988566 - type: f1 - value: 49.21139492760165 + value: 57.43015543162361 - task: type: Classification dataset: @@ -3378,9 +3688,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 54.182918628110286 + value: 59.492266308002705 - type: f1 - value: 52.039181194514875 + value: 56.885590563156455 - task: type: Classification dataset: @@ -3391,9 +3701,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 55.59852051109617 + value: 60.477471418964356 - type: f1 - value: 53.060686908268394 + value: 57.87047944039945 - task: type: Classification dataset: @@ -3404,9 +3714,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 57.726967047747145 + value: 62.07800941492938 - type: f1 - value: 54.645702631584584 + value: 59.340232908410265 - task: type: Classification dataset: @@ -3417,9 +3727,9 @@ model-index: revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy - value: 51.42568930733018 + value: 56.73167451244117 - type: f1 - value: 50.882328594696006 + value: 55.29236319279749 - task: type: Classification dataset: @@ -3430,9 +3740,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 60.41694687289846 + value: 64.05850706119705 - type: f1 - value: 58.690860679703725 + value: 62.20100273658395 - task: type: Classification dataset: @@ -3443,9 +3753,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 59.48890383322125 + value: 63.24142568930733 - type: f1 - value: 58.39835688515581 + value: 62.045023522098205 - task: type: Classification dataset: @@ -3456,9 +3766,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 60.238735709482185 + value: 63.685272360457304 - type: f1 - value: 59.72662500042014 + value: 63.315744557403285 - task: type: Classification dataset: @@ -3469,9 +3779,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 57.044384667115 + value: 60.85743106926698 - type: f1 - value: 55.384095671817 + value: 59.106917986505636 - task: type: Classification dataset: @@ -3482,9 +3792,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.35776731674514 + value: 67.1654337592468 - type: f1 - value: 62.74311932650383 + value: 65.66986920813582 - task: type: Classification dataset: @@ -3495,9 +3805,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 51.67787491593814 + value: 56.519838601210495 - type: f1 - value: 50.38547848410452 + value: 54.73278620356587 - task: type: Classification dataset: @@ -3508,9 +3818,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.98251513113653 + value: 67.76395427034298 - type: f1 - value: 61.81962359822365 + value: 66.3447645997219 - task: type: Classification dataset: @@ -3521,9 +3831,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 63.28177538668459 + value: 67.47814391392065 - type: f1 - value: 62.03411861425649 + value: 66.32841368787447 - task: type: Classification dataset: @@ -3534,9 +3844,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.29119031607263 + value: 70.22864828513787 - type: f1 - value: 65.02800460526542 + value: 69.02774052818218 - task: type: Classification dataset: @@ -3547,9 +3857,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.14593140551446 + value: 69.04841963685273 - type: f1 - value: 62.99257031840126 + value: 67.70789401248665 - task: type: Classification dataset: @@ -3560,9 +3870,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.43375924680565 + value: 69.08204438466711 - type: f1 - value: 64.62403786298874 + value: 68.39277940460933 - task: type: Classification dataset: @@ -3573,9 +3883,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 68.90719569603229 + value: 72.10154673839946 - type: f1 - value: 67.32949258170802 + value: 70.7737194288215 - task: type: Classification dataset: @@ -3586,9 +3896,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.00470746469402 + value: 67.16207128446537 - type: f1 - value: 62.923780468763525 + value: 66.2311820377212 - task: type: Classification dataset: @@ -3599,9 +3909,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 55.71284465366511 + value: 63.019502353732335 - type: f1 - value: 56.08069685713033 + value: 62.105500895318656 - task: type: Classification dataset: @@ -3612,9 +3922,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.3752521856086 + value: 68.82985877605918 - type: f1 - value: 64.90995811394924 + value: 67.4894449433449 - task: type: Classification dataset: @@ -3625,9 +3935,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.858103564223256 + value: 66.89643577673168 - type: f1 - value: 61.62638799458199 + value: 65.45745898521055 - task: type: Classification dataset: @@ -3638,9 +3948,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.2273032952253 + value: 69.32750504371216 - type: f1 - value: 64.95618816406058 + value: 68.19665323990438 - task: type: Classification dataset: @@ -3651,9 +3961,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.67652992602556 + value: 65.8238063214526 - type: f1 - value: 61.33438873938238 + value: 64.60872984606974 - task: type: Classification dataset: @@ -3664,9 +3974,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.45729657027573 + value: 68.98117014122394 - type: f1 - value: 63.99738359920934 + value: 67.66697147027641 - task: type: Classification dataset: @@ -3677,9 +3987,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 59.0719569603228 + value: 63.137188971082715 - type: f1 - value: 57.518504167063234 + value: 61.58358081191463 - task: type: Classification dataset: @@ -3690,9 +4000,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.13315400134499 + value: 70.0437121721587 - type: f1 - value: 65.160633131251 + value: 69.06747206775307 - task: type: Classification dataset: @@ -3703,9 +4013,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.61398789509079 + value: 70.67585743106926 - type: f1 - value: 65.79824135316741 + value: 70.08618915891508 - task: type: Classification dataset: @@ -3716,9 +4026,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 56.90316072629456 + value: 59.788164088769335 - type: f1 - value: 54.86322025311521 + value: 57.91398932676417 - task: type: Classification dataset: @@ -3729,9 +4039,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 56.94687289845326 + value: 61.03227975790182 - type: f1 - value: 56.12621536279501 + value: 60.044432258486715 - task: type: Classification dataset: @@ -3742,9 +4052,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 42.66308002689979 + value: 49.051782111634154 - type: f1 - value: 38.86253489600552 + value: 45.434581931581555 - task: type: Classification dataset: @@ -3755,9 +4065,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 61.20712844653665 + value: 63.78278412911902 - type: f1 - value: 59.38664125148938 + value: 62.106197625881535 - task: type: Classification dataset: @@ -3768,9 +4078,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.16005379959651 + value: 69.59986550100874 - type: f1 - value: 65.37496105527057 + value: 68.94355682848476 - task: type: Classification dataset: @@ -3781,9 +4091,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 55.46738399462004 + value: 59.97310020174847 - type: f1 - value: 54.74655536412335 + value: 59.09912773329623 - task: type: Classification dataset: @@ -3794,9 +4104,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.8675184936113 + value: 69.20309347679893 - type: f1 - value: 64.4167690022513 + value: 67.90665916607239 - task: type: Classification dataset: @@ -3807,9 +4117,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 59.34767989240082 + value: 62.72024209818427 - type: f1 - value: 57.584089752919766 + value: 60.77165334831407 - task: type: Classification dataset: @@ -3820,9 +4130,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.92938802958977 + value: 67.87155346334902 - type: f1 - value: 62.689467476962534 + value: 65.7906032446679 - task: type: Classification dataset: @@ -3833,9 +4143,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 60.860793544048406 + value: 64.97646267652992 - type: f1 - value: 59.642494854830964 + value: 63.89390215791396 - task: type: Classification dataset: @@ -3846,9 +4156,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 61.99058507061197 + value: 65.81371889710827 - type: f1 - value: 60.80631394200557 + value: 64.39323436519936 - task: type: Classification dataset: @@ -3859,9 +4169,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.773369199731 + value: 69.79825151311366 - type: f1 - value: 64.59673968371376 + value: 68.53789900442244 - task: type: Classification dataset: @@ -3872,9 +4182,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 66.54673839946201 + value: 69.98991257565568 - type: f1 - value: 65.39512803006458 + value: 68.93867074879778 - task: type: Classification dataset: @@ -3885,9 +4195,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 63.64492266308002 + value: 67.50168123739071 - type: f1 - value: 62.96480563325382 + value: 66.7457644903972 - task: type: Classification dataset: @@ -3898,9 +4208,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.03833221250841 + value: 67.52521856086078 - type: f1 - value: 63.277354377232754 + value: 66.83370797374445 - task: type: Classification dataset: @@ -3911,9 +4221,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 63.09683927370544 + value: 67.96234028244787 - type: f1 - value: 63.105668759138 + value: 67.58983110064196 - task: type: Classification dataset: @@ -3924,9 +4234,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.635507733692 + value: 69.56624075319435 - type: f1 - value: 64.1835797433392 + value: 68.35270162147211 - task: type: Classification dataset: @@ -3937,9 +4247,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.96973772696705 + value: 68.48352387357095 - type: f1 - value: 63.000024177311595 + value: 66.66973143886908 - task: type: Classification dataset: @@ -3950,9 +4260,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.7848016139879 + value: 67.92535305985206 - type: f1 - value: 63.36081856889688 + value: 66.52058462942483 - task: type: Classification dataset: @@ -3963,9 +4273,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 59.97982515131136 + value: 63.184263618022875 - type: f1 - value: 58.457979351949675 + value: 61.71153164960602 - task: type: Classification dataset: @@ -3976,9 +4286,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 61.19367854741089 + value: 64.8453261600538 - type: f1 - value: 60.244347062989064 + value: 63.863209439112346 - task: type: Classification dataset: @@ -3989,9 +4299,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.67989240080699 + value: 65.39340954942838 - type: f1 - value: 61.03003364010584 + value: 63.85484524633183 - task: type: Classification dataset: @@ -4002,9 +4312,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 64.70410221923335 + value: 67.9892400806994 - type: f1 - value: 63.194634988237894 + value: 66.57022479007357 - task: type: Classification dataset: @@ -4015,9 +4325,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 60.45057162071284 + value: 63.399462004034966 - type: f1 - value: 58.75729037108071 + value: 61.62381473991175 - task: type: Classification dataset: @@ -4028,9 +4338,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 58.315400134498994 + value: 65.773369199731 - type: f1 - value: 59.46974195941193 + value: 65.58317907780943 - task: type: Classification dataset: @@ -4041,9 +4351,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.562205783456626 + value: 65.8069939475454 - type: f1 - value: 61.18682850669083 + value: 64.47027323557235 - task: type: Classification dataset: @@ -4054,9 +4364,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 62.868190988567584 + value: 66.51647612642904 - type: f1 - value: 62.04867947782604 + value: 65.66061210324213 - task: type: Classification dataset: @@ -4067,9 +4377,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 65.35642232683256 + value: 68.88365837256221 - type: f1 - value: 63.940631681609915 + value: 67.56956454874091 - task: type: Classification dataset: @@ -4080,9 +4390,9 @@ model-index: revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy - value: 58.81640887693342 + value: 63.29858776059179 - type: f1 - value: 58.4125957354379 + value: 62.76318771484755 - task: type: Retrieval dataset: @@ -4162,7 +4472,7 @@ model-index: revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure - value: 19.340284691485483 + value: 19.061819627060558 - task: type: Clustering dataset: @@ -4173,7 +4483,7 @@ model-index: revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure - value: 17.003121027783283 + value: 19.79520446745267 - task: type: Reranking dataset: @@ -4184,9 +4494,9 @@ model-index: revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map - value: 26.881341526634174 + value: 26.881162218991285 - type: mrr - value: 27.23083862187728 + value: 27.23201335662217 - task: type: Classification dataset: @@ -4197,9 +4507,9 @@ model-index: revision: 46958b007a63fdbf239b7672c25d0bea67b5ea1a metrics: - type: accuracy - value: 54.08666666666667 + value: 57.69 - type: f1 - value: 53.05912174796259 + value: 57.370451927892695 - task: type: Retrieval dataset: @@ -4269,6 +4579,75 @@ model-index: value: 0.931 - type: recall_at_5 value: 1.698 + - task: + type: Retrieval + dataset: + type: nfcorpus-pl + name: MTEB NFCorpus-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 0.307 + - type: map_at_10 + value: 0.835 + - type: map_at_100 + value: 1.503 + - type: map_at_1000 + value: 2.263 + - type: map_at_3 + value: 0.503 + - type: map_at_5 + value: 0.567 + - type: mrr_at_1 + value: 4.025 + - type: mrr_at_10 + value: 9.731 + - type: mrr_at_100 + value: 11.229 + - type: mrr_at_1000 + value: 11.34 + - type: mrr_at_3 + value: 6.811 + - type: mrr_at_5 + value: 8.126999999999999 + - type: ndcg_at_1 + value: 3.56 + - type: ndcg_at_10 + value: 4.596 + - type: ndcg_at_100 + value: 7.567 + - type: ndcg_at_1000 + value: 17.76 + - type: ndcg_at_3 + value: 3.52 + - type: ndcg_at_5 + value: 3.823 + - type: precision_at_1 + value: 4.025 + - type: precision_at_10 + value: 4.334 + - type: precision_at_100 + value: 2.842 + - type: precision_at_1000 + value: 1.506 + - type: precision_at_3 + value: 3.818 + - type: precision_at_5 + value: 4.149 + - type: recall_at_1 + value: 0.307 + - type: recall_at_10 + value: 2.543 + - type: recall_at_100 + value: 12.152000000000001 + - type: recall_at_1000 + value: 46.878 + - type: recall_at_3 + value: 0.755 + - type: recall_at_5 + value: 0.975 - task: type: Retrieval dataset: @@ -4417,9 +4796,9 @@ model-index: revision: 07b99ab3363c2e7f8f87015b01c21f4d9b917ce3 metrics: - type: accuracy - value: 48.720703125 + value: 48.251953125 - type: f1 - value: 44.40194414610097 + value: 45.42526611578402 - task: type: Classification dataset: @@ -4430,9 +4809,9 @@ model-index: revision: e254179d18ab0165fdb6dbef91178266222bee2a metrics: - type: accuracy - value: 46.626666666666665 + value: 48.403333333333336 - type: f1 - value: 44.771861545457476 + value: 47.9287124185198 - task: type: BitextMining dataset: @@ -4443,13 +4822,13 @@ model-index: revision: None metrics: - type: accuracy - value: 94.73684210526315 - - type: f1 value: 93.85964912280701 + - type: f1 + value: 92.98245614035088 - type: precision - value: 93.42105263157895 + value: 92.54385964912281 - type: recall - value: 94.73684210526315 + value: 93.85964912280701 - task: type: Classification dataset: @@ -4460,11 +4839,11 @@ model-index: revision: f7393532774c66312378d30b197610b43d751972 metrics: - type: accuracy - value: 55.408333333333324 + value: 55.991666666666674 - type: ap - value: 53.03584049725229 + value: 53.417849849746226 - type: f1 - value: 55.0030558323002 + value: 55.757916182475384 - task: type: PairClassification dataset: @@ -4477,7 +4856,7 @@ model-index: - type: cos_sim_accuracy value: 54.68327016783974 - type: cos_sim_ap - value: 55.175113037501625 + value: 55.175059616546406 - type: cos_sim_f1 value: 67.81733189500179 - type: cos_sim_precision @@ -4485,41 +4864,41 @@ model-index: - type: cos_sim_recall value: 99.57761351636748 - type: dot_accuracy - value: 53.3838657282079 + value: 54.68327016783974 - type: dot_ap - value: 54.09970939118489 + value: 55.175059616546406 - type: dot_f1 - value: 67.81485468245427 + value: 67.81733189500179 - type: dot_precision - value: 51.358695652173914 + value: 51.41766630316249 - type: dot_recall - value: 99.78880675818374 + value: 99.57761351636748 - type: euclidean_accuracy - value: 52.680021656740664 + value: 54.68327016783974 - type: euclidean_ap - value: 54.61964760120384 + value: 55.17510180566365 - type: euclidean_f1 - value: 67.86743515850145 + value: 67.81733189500179 - type: euclidean_precision - value: 51.50355385456533 + value: 51.41766630316249 - type: euclidean_recall - value: 99.47201689545935 + value: 99.57761351636748 - type: manhattan_accuracy - value: 52.84244721169464 + value: 55.44125609095831 - type: manhattan_ap - value: 54.95963401318357 + value: 55.76283671826867 - type: manhattan_f1 - value: 67.96818510484454 + value: 68.05905653583004 - type: manhattan_precision - value: 51.67674546454095 + value: 51.63934426229508 - type: manhattan_recall - value: 99.26082365364309 + value: 99.78880675818374 - type: max_accuracy - value: 54.68327016783974 + value: 55.44125609095831 - type: max_ap - value: 55.175113037501625 + value: 55.76283671826867 - type: max_f1 - value: 67.96818510484454 + value: 68.05905653583004 - task: type: Classification dataset: @@ -4530,11 +4909,11 @@ model-index: revision: e610f2ebd179a8fda30ae534c3878750a96db120 metrics: - type: accuracy - value: 71.38 + value: 75.64 - type: ap - value: 67.98361406325826 + value: 71.45085103287833 - type: f1 - value: 71.32677133367216 + value: 75.52254495697326 - task: type: Classification dataset: @@ -4545,11 +4924,11 @@ model-index: revision: None metrics: - type: accuracy - value: 73.79090645815232 + value: 73.86620330147699 - type: ap - value: 79.78709287447715 + value: 80.58015815306322 - type: f1 - value: 71.11540289567428 + value: 71.49082510883872 - task: type: STS dataset: @@ -4560,17 +4939,17 @@ model-index: revision: 9c6a90e430ac22b5779fb019a23e820b11a8b5e1 metrics: - type: cos_sim_pearson - value: 29.52361484634536 + value: 29.52361689421863 - type: cos_sim_spearman - value: 32.749971481829185 + value: 32.750058577257875 - type: euclidean_pearson - value: 32.54178605588255 + value: 34.583472972871796 - type: euclidean_spearman - value: 31.470626091963805 + value: 32.75328764421994 - type: manhattan_pearson - value: 32.59570732501661 + value: 34.727366510326995 - type: manhattan_spearman - value: 31.45843300214921 + value: 32.787167142114214 - task: type: PairClassification dataset: @@ -4591,19 +4970,19 @@ model-index: - type: cos_sim_recall value: 99.83443708609272 - type: dot_accuracy - value: 64.1 + value: 71.1 - type: dot_ap - value: 68.24516982673607 + value: 85.36544548691204 - type: dot_f1 - value: 75.9412890874282 + value: 75.23393636930756 - type: dot_precision - value: 61.78608515057113 + value: 60.36036036036037 - type: dot_recall - value: 98.50993377483444 + value: 99.83443708609272 - type: euclidean_accuracy - value: 73.0 + value: 71.1 - type: euclidean_ap - value: 85.77605840690839 + value: 85.36544548691205 - type: euclidean_f1 value: 75.23393636930756 - type: euclidean_precision @@ -4611,9 +4990,9 @@ model-index: - type: euclidean_recall value: 99.83443708609272 - type: manhattan_accuracy - value: 73.0 + value: 71.1 - type: manhattan_ap - value: 85.77723100027544 + value: 85.33853868545614 - type: manhattan_f1 value: 75.23393636930756 - type: manhattan_precision @@ -4621,11 +5000,11 @@ model-index: - type: manhattan_recall value: 99.83443708609272 - type: max_accuracy - value: 73.0 + value: 71.1 - type: max_ap - value: 85.77723100027544 + value: 85.36544548691205 - type: max_f1 - value: 75.9412890874282 + value: 75.23393636930756 - task: type: PairClassification dataset: @@ -4646,41 +5025,426 @@ model-index: - type: cos_sim_recall value: 91.15853658536585 - type: dot_accuracy - value: 85.9925788497217 + value: 90.81632653061224 - type: dot_ap - value: 83.51557404204843 + value: 91.97693749083473 - type: dot_f1 - value: 78.0141843971631 + value: 85.55078683834049 - type: dot_precision - value: 72.94429708222812 + value: 80.59299191374663 - type: dot_recall - value: 83.84146341463415 + value: 91.15853658536585 - type: euclidean_accuracy - value: 88.12615955473099 + value: 90.81632653061224 - type: euclidean_ap - value: 88.83596272873487 + value: 91.97693749083473 - type: euclidean_f1 - value: 80.46647230320698 + value: 85.55078683834049 - type: euclidean_precision - value: 77.09497206703911 + value: 80.59299191374663 - type: euclidean_recall - value: 84.14634146341463 + value: 91.15853658536585 - type: manhattan_accuracy - value: 88.31168831168831 + value: 90.9090909090909 - type: manhattan_ap - value: 89.15769755969164 + value: 92.043441286281 - type: manhattan_f1 - value: 80.62678062678062 + value: 85.34482758620689 - type: manhattan_precision - value: 75.66844919786097 + value: 80.70652173913044 - type: manhattan_recall - value: 86.28048780487805 + value: 90.54878048780488 - type: max_accuracy - value: 90.81632653061224 + value: 90.9090909090909 - type: max_ap - value: 91.97693749083473 + value: 92.043441286281 - type: max_f1 value: 85.55078683834049 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (de) + config: de + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 70.35 + - type: cos_sim_ap + value: 72.01641717127626 + - type: cos_sim_f1 + value: 64.49511400651467 + - type: cos_sim_precision + value: 55.26315789473685 + - type: cos_sim_recall + value: 77.43016759776536 + - type: dot_accuracy + value: 70.35 + - type: dot_ap + value: 72.06599137974572 + - type: dot_f1 + value: 64.49511400651467 + - type: dot_precision + value: 55.26315789473685 + - type: dot_recall + value: 77.43016759776536 + - type: euclidean_accuracy + value: 70.35 + - type: euclidean_ap + value: 71.92019289154159 + - type: euclidean_f1 + value: 64.49511400651467 + - type: euclidean_precision + value: 55.26315789473685 + - type: euclidean_recall + value: 77.43016759776536 + - type: manhattan_accuracy + value: 70.35 + - type: manhattan_ap + value: 71.92979188519502 + - type: manhattan_f1 + value: 64.60409019402202 + - type: manhattan_precision + value: 60.86956521739131 + - type: manhattan_recall + value: 68.8268156424581 + - type: max_accuracy + value: 70.35 + - type: max_ap + value: 72.06599137974572 + - type: max_f1 + value: 64.60409019402202 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (en) + config: en + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 71.0 + - type: cos_sim_ap + value: 74.73017292645147 + - type: cos_sim_f1 + value: 66.73427991886409 + - type: cos_sim_precision + value: 61.78403755868545 + - type: cos_sim_recall + value: 72.54685777287762 + - type: dot_accuracy + value: 71.0 + - type: dot_ap + value: 74.73017292645147 + - type: dot_f1 + value: 66.73427991886409 + - type: dot_precision + value: 61.78403755868545 + - type: dot_recall + value: 72.54685777287762 + - type: euclidean_accuracy + value: 71.0 + - type: euclidean_ap + value: 74.73013082197343 + - type: euclidean_f1 + value: 66.73427991886409 + - type: euclidean_precision + value: 61.78403755868545 + - type: euclidean_recall + value: 72.54685777287762 + - type: manhattan_accuracy + value: 70.95 + - type: manhattan_ap + value: 74.71203917486744 + - type: manhattan_f1 + value: 66.86868686868686 + - type: manhattan_precision + value: 61.696178937558244 + - type: manhattan_recall + value: 72.98787210584344 + - type: max_accuracy + value: 71.0 + - type: max_ap + value: 74.73017292645147 + - type: max_f1 + value: 66.86868686868686 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (es) + config: es + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 67.7 + - type: cos_sim_ap + value: 69.70320170421651 + - type: cos_sim_f1 + value: 62.55625562556255 + - type: cos_sim_precision + value: 52.851711026615966 + - type: cos_sim_recall + value: 76.62624035281146 + - type: dot_accuracy + value: 67.7 + - type: dot_ap + value: 69.70320170421651 + - type: dot_f1 + value: 62.55625562556255 + - type: dot_precision + value: 52.851711026615966 + - type: dot_recall + value: 76.62624035281146 + - type: euclidean_accuracy + value: 67.7 + - type: euclidean_ap + value: 69.70320170421651 + - type: euclidean_f1 + value: 62.55625562556255 + - type: euclidean_precision + value: 52.851711026615966 + - type: euclidean_recall + value: 76.62624035281146 + - type: manhattan_accuracy + value: 67.75 + - type: manhattan_ap + value: 69.67833816050764 + - type: manhattan_f1 + value: 62.734082397003746 + - type: manhattan_precision + value: 54.515866558177386 + - type: manhattan_recall + value: 73.8699007717751 + - type: max_accuracy + value: 67.75 + - type: max_ap + value: 69.70320170421651 + - type: max_f1 + value: 62.734082397003746 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (fr) + config: fr + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 69.0 + - type: cos_sim_ap + value: 71.36406639969131 + - type: cos_sim_f1 + value: 64.45993031358886 + - type: cos_sim_precision + value: 53.12275664034458 + - type: cos_sim_recall + value: 81.94905869324474 + - type: dot_accuracy + value: 69.0 + - type: dot_ap + value: 71.2599779415656 + - type: dot_f1 + value: 64.45993031358886 + - type: dot_precision + value: 53.12275664034458 + - type: dot_recall + value: 81.94905869324474 + - type: euclidean_accuracy + value: 69.0 + - type: euclidean_ap + value: 71.3126257271965 + - type: euclidean_f1 + value: 64.45993031358886 + - type: euclidean_precision + value: 53.12275664034458 + - type: euclidean_recall + value: 81.94905869324474 + - type: manhattan_accuracy + value: 69.0 + - type: manhattan_ap + value: 71.29361764028188 + - type: manhattan_f1 + value: 64.54789615040288 + - type: manhattan_precision + value: 54.16979714500376 + - type: manhattan_recall + value: 79.84496124031007 + - type: max_accuracy + value: 69.0 + - type: max_ap + value: 71.36406639969131 + - type: max_f1 + value: 64.54789615040288 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (ja) + config: ja + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 63.849999999999994 + - type: cos_sim_ap + value: 60.914955950361026 + - type: cos_sim_f1 + value: 62.4556422995032 + - type: cos_sim_precision + value: 45.47803617571059 + - type: cos_sim_recall + value: 99.66024915062289 + - type: dot_accuracy + value: 63.849999999999994 + - type: dot_ap + value: 60.808056565465506 + - type: dot_f1 + value: 62.4556422995032 + - type: dot_precision + value: 45.47803617571059 + - type: dot_recall + value: 99.66024915062289 + - type: euclidean_accuracy + value: 63.849999999999994 + - type: euclidean_ap + value: 60.8231492677072 + - type: euclidean_f1 + value: 62.4556422995032 + - type: euclidean_precision + value: 45.47803617571059 + - type: euclidean_recall + value: 99.66024915062289 + - type: manhattan_accuracy + value: 63.800000000000004 + - type: manhattan_ap + value: 60.86392751846975 + - type: manhattan_f1 + value: 62.43348705214614 + - type: manhattan_precision + value: 45.45454545454545 + - type: manhattan_recall + value: 99.66024915062289 + - type: max_accuracy + value: 63.849999999999994 + - type: max_ap + value: 60.914955950361026 + - type: max_f1 + value: 62.4556422995032 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (ko) + config: ko + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 61.1 + - type: cos_sim_ap + value: 58.40339411735916 + - type: cos_sim_f1 + value: 62.7906976744186 + - type: cos_sim_precision + value: 46.55172413793103 + - type: cos_sim_recall + value: 96.42857142857143 + - type: dot_accuracy + value: 61.1 + - type: dot_ap + value: 58.439189685586456 + - type: dot_f1 + value: 62.7906976744186 + - type: dot_precision + value: 46.55172413793103 + - type: dot_recall + value: 96.42857142857143 + - type: euclidean_accuracy + value: 61.1 + - type: euclidean_ap + value: 58.34968788203145 + - type: euclidean_f1 + value: 62.7906976744186 + - type: euclidean_precision + value: 46.55172413793103 + - type: euclidean_recall + value: 96.42857142857143 + - type: manhattan_accuracy + value: 61.1 + - type: manhattan_ap + value: 58.31504446861402 + - type: manhattan_f1 + value: 62.636562272396226 + - type: manhattan_precision + value: 46.48648648648649 + - type: manhattan_recall + value: 95.98214285714286 + - type: max_accuracy + value: 61.1 + - type: max_ap + value: 58.439189685586456 + - type: max_f1 + value: 62.7906976744186 + - task: + type: PairClassification + dataset: + type: paws-x + name: MTEB PawsX (zh) + config: zh + split: test + revision: 8a04d940a42cd40658986fdd8e3da561533a3646 + metrics: + - type: cos_sim_accuracy + value: 64.2 + - type: cos_sim_ap + value: 63.73722153283802 + - type: cos_sim_f1 + value: 62.52707581227437 + - type: cos_sim_precision + value: 46.16204690831556 + - type: cos_sim_recall + value: 96.86800894854586 + - type: dot_accuracy + value: 64.2 + - type: dot_ap + value: 63.67335241021108 + - type: dot_f1 + value: 62.52707581227437 + - type: dot_precision + value: 46.16204690831556 + - type: dot_recall + value: 96.86800894854586 + - type: euclidean_accuracy + value: 64.2 + - type: euclidean_ap + value: 63.77399571117368 + - type: euclidean_f1 + value: 62.52707581227437 + - type: euclidean_precision + value: 46.16204690831556 + - type: euclidean_recall + value: 96.86800894854586 + - type: manhattan_accuracy + value: 64.5 + - type: manhattan_ap + value: 63.747406783360816 + - type: manhattan_f1 + value: 62.58601955813112 + - type: manhattan_precision + value: 46.27745045527584 + - type: manhattan_recall + value: 96.64429530201343 + - type: max_accuracy + value: 64.5 + - type: max_ap + value: 63.77399571117368 + - type: max_f1 + value: 62.58601955813112 - task: type: Classification dataset: @@ -4691,9 +5455,9 @@ model-index: revision: None metrics: - type: accuracy - value: 50.72022160664821 + value: 52.797783933518005 - type: f1 - value: 51.12376375708585 + value: 53.84971294048786 - task: type: Classification dataset: @@ -4704,9 +5468,9 @@ model-index: revision: None metrics: - type: accuracy - value: 33.36032388663968 + value: 38.40080971659919 - type: f1 - value: 27.16896572816315 + value: 30.38990873840624 - task: type: STS dataset: @@ -4717,17 +5481,86 @@ model-index: revision: 790b0510dc52b1553e8c49f3d2afb48c0e5c48b7 metrics: - type: cos_sim_pearson - value: 23.34232603207876 + value: 23.34232568997104 - type: cos_sim_spearman - value: 24.4795842135422 + value: 24.47961936211083 - type: euclidean_pearson - value: 19.94484261154701 + value: 22.03140944610336 - type: euclidean_spearman - value: 20.678133816020438 + value: 24.47949166265398 - type: manhattan_pearson - value: 22.39245233528255 + value: 25.542406448726908 - type: manhattan_spearman - value: 22.93218231516663 + value: 28.655724283839533 + - task: + type: Retrieval + dataset: + type: quora-pl + name: MTEB Quora-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 59.938 + - type: map_at_10 + value: 72.734 + - type: map_at_100 + value: 73.564 + - type: map_at_1000 + value: 73.602 + - type: map_at_3 + value: 69.707 + - type: map_at_5 + value: 71.515 + - type: mrr_at_1 + value: 69.28 + - type: mrr_at_10 + value: 76.97500000000001 + - type: mrr_at_100 + value: 77.27199999999999 + - type: mrr_at_1000 + value: 77.28 + - type: mrr_at_3 + value: 75.355 + - type: mrr_at_5 + value: 76.389 + - type: ndcg_at_1 + value: 69.33 + - type: ndcg_at_10 + value: 77.61099999999999 + - type: ndcg_at_100 + value: 80.02 + - type: ndcg_at_1000 + value: 80.487 + - type: ndcg_at_3 + value: 73.764 + - type: ndcg_at_5 + value: 75.723 + - type: precision_at_1 + value: 69.33 + - type: precision_at_10 + value: 11.917 + - type: precision_at_100 + value: 1.447 + - type: precision_at_1000 + value: 0.154 + - type: precision_at_3 + value: 32.29 + - type: precision_at_5 + value: 21.432000000000002 + - type: recall_at_1 + value: 59.938 + - type: recall_at_10 + value: 87.252 + - type: recall_at_100 + value: 96.612 + - type: recall_at_1000 + value: 99.388 + - type: recall_at_3 + value: 76.264 + - type: recall_at_5 + value: 81.71000000000001 - task: type: Retrieval dataset: @@ -4738,41 +5571,41 @@ model-index: revision: None metrics: - type: map_at_1 - value: 61.451 + value: 61.458999999999996 - type: map_at_10 - value: 73.898 + value: 73.90299999999999 - type: map_at_100 - value: 74.72800000000001 + value: 74.733 - type: map_at_1000 - value: 74.766 + value: 74.771 - type: map_at_3 - value: 70.994 + value: 70.999 - type: map_at_5 - value: 72.74000000000001 + value: 72.745 - type: mrr_at_1 - value: 70.94 + value: 70.93 - type: mrr_at_10 - value: 78.35600000000001 + value: 78.353 - type: mrr_at_100 - value: 78.64 + value: 78.636 - type: mrr_at_1000 - value: 78.647 + value: 78.644 - type: mrr_at_3 - value: 76.912 + value: 76.908 - type: mrr_at_5 - value: 77.81 + value: 77.807 - type: ndcg_at_1 value: 70.93 - type: ndcg_at_10 - value: 78.622 + value: 78.625 - type: ndcg_at_100 - value: 81.00699999999999 + value: 81.01 - type: ndcg_at_1000 - value: 81.453 + value: 81.45700000000001 - type: ndcg_at_3 - value: 75.03999999999999 + value: 75.045 - type: ndcg_at_5 - value: 76.839 + value: 76.84299999999999 - type: precision_at_1 value: 70.93 - type: precision_at_10 @@ -4786,7 +5619,7 @@ model-index: - type: precision_at_5 value: 21.598 - type: recall_at_1 - value: 61.451 + value: 61.458999999999996 - type: recall_at_10 value: 87.608 - type: recall_at_100 @@ -4794,7 +5627,7 @@ model-index: - type: recall_at_1000 value: 99.445 - type: recall_at_3 - value: 77.348 + value: 77.354 - type: recall_at_5 value: 82.334 - task: @@ -4807,7 +5640,7 @@ model-index: revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure - value: 18.928966218247353 + value: 28.519889100999958 - task: type: Clustering dataset: @@ -4818,7 +5651,7 @@ model-index: revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure - value: 35.948929675640414 + value: 38.62765374782771 - task: type: Retrieval dataset: @@ -4888,6 +5721,75 @@ model-index: value: 1.0699999999999998 - type: recall_at_5 value: 1.27 + - task: + type: Retrieval + dataset: + type: scidocs-pl + name: MTEB SCIDOCS-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 0.32 + - type: map_at_10 + value: 0.676 + - type: map_at_100 + value: 0.847 + - type: map_at_1000 + value: 1.032 + - type: map_at_3 + value: 0.5369999999999999 + - type: map_at_5 + value: 0.592 + - type: mrr_at_1 + value: 1.6 + - type: mrr_at_10 + value: 2.863 + - type: mrr_at_100 + value: 3.334 + - type: mrr_at_1000 + value: 3.5479999999999996 + - type: mrr_at_3 + value: 2.317 + - type: mrr_at_5 + value: 2.587 + - type: ndcg_at_1 + value: 1.6 + - type: ndcg_at_10 + value: 1.397 + - type: ndcg_at_100 + value: 2.819 + - type: ndcg_at_1000 + value: 9.349 + - type: ndcg_at_3 + value: 1.3 + - type: ndcg_at_5 + value: 1.1079999999999999 + - type: precision_at_1 + value: 1.6 + - type: precision_at_10 + value: 0.74 + - type: precision_at_100 + value: 0.295 + - type: precision_at_1000 + value: 0.194 + - type: precision_at_3 + value: 1.2 + - type: precision_at_5 + value: 0.96 + - type: recall_at_1 + value: 0.32 + - type: recall_at_10 + value: 1.505 + - type: recall_at_100 + value: 5.988 + - type: recall_at_1000 + value: 39.308 + - type: recall_at_3 + value: 0.72 + - type: recall_at_5 + value: 0.9650000000000001 - task: type: PairClassification dataset: @@ -4900,7 +5802,7 @@ model-index: - type: cos_sim_accuracy value: 73.84834896045659 - type: cos_sim_ap - value: 55.48406649230719 + value: 55.484124732566606 - type: cos_sim_f1 value: 57.34228187919464 - type: cos_sim_precision @@ -4908,41 +5810,41 @@ model-index: - type: cos_sim_recall value: 76.06837606837607 - type: dot_accuracy - value: 72.6049735018345 + value: 73.84834896045659 - type: dot_ap - value: 47.4643427557602 + value: 55.48400003295399 - type: dot_f1 - value: 55.22423104015027 + value: 57.34228187919464 - type: dot_precision - value: 41.190893169877405 + value: 46.01464885825076 - type: dot_recall - value: 83.76068376068376 + value: 76.06837606837607 - type: euclidean_accuracy - value: 74.01141459437423 + value: 73.84834896045659 - type: euclidean_ap - value: 55.32291633102242 + value: 55.48407331902175 - type: euclidean_f1 - value: 56.970649895178184 + value: 57.34228187919464 - type: euclidean_precision - value: 45.066334991708125 + value: 46.01464885825076 - type: euclidean_recall - value: 77.42165242165242 + value: 76.06837606837607 - type: manhattan_accuracy - value: 73.99103139013454 + value: 73.80758255197716 - type: manhattan_ap - value: 55.25996778114356 + value: 55.42477275597209 - type: manhattan_f1 - value: 57.0203644158628 + value: 57.55860953920776 - type: manhattan_precision - value: 45.70446735395189 + value: 46.29388816644994 - type: manhattan_recall - value: 75.78347578347578 + value: 76.06837606837607 - type: max_accuracy - value: 74.01141459437423 + value: 73.84834896045659 - type: max_ap - value: 55.48406649230719 + value: 55.484124732566606 - type: max_f1 - value: 57.34228187919464 + value: 57.55860953920776 - task: type: STS dataset: @@ -4953,17 +5855,17 @@ model-index: revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson - value: 67.0394316443087 + value: 67.03943120783973 - type: cos_sim_spearman - value: 62.93973839554845 + value: 62.93971145260584 - type: euclidean_pearson - value: 57.60094512966203 + value: 64.13947263916926 - type: euclidean_spearman - value: 57.05926985559664 + value: 62.93972324235839 - type: manhattan_pearson - value: 57.53054316732484 + value: 64.11295322654566 - type: manhattan_spearman - value: 56.98810707222501 + value: 62.92816122293202 - task: type: STS dataset: @@ -4974,17 +5876,17 @@ model-index: revision: None metrics: - type: cos_sim_pearson - value: 67.75034195626081 + value: 67.75034167381077 - type: cos_sim_spearman - value: 62.98156510096241 + value: 62.98158872758643 - type: euclidean_pearson - value: 60.102373885669 + value: 64.25794794439082 - type: euclidean_spearman - value: 58.78567620580185 + value: 62.981566596223125 - type: manhattan_pearson - value: 60.06786982256782 + value: 64.25439446502435 - type: manhattan_spearman - value: 58.782787914089305 + value: 63.01301439900365 - task: type: STS dataset: @@ -4995,17 +5897,17 @@ model-index: revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson - value: 61.62220407968201 + value: 61.622204530882755 - type: cos_sim_spearman - value: 65.46331444956428 + value: 65.4632047656541 - type: euclidean_pearson - value: 53.17721859223576 + value: 59.21529585527598 - type: euclidean_spearman - value: 62.26490113361859 + value: 65.4638163967956 - type: manhattan_pearson - value: 53.24730859766875 + value: 59.39341472707122 - type: manhattan_spearman - value: 62.27695125302589 + value: 65.57635757250173 - task: type: STS dataset: @@ -5016,17 +5918,17 @@ model-index: revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson - value: 60.32974355127381 + value: 60.329743331971486 - type: cos_sim_spearman - value: 62.786126823027246 + value: 62.78607195958339 - type: euclidean_pearson - value: 48.85507668127239 + value: 62.07415212138581 - type: euclidean_spearman - value: 50.87786603451179 + value: 62.78618151904129 - type: manhattan_pearson - value: 49.12859466063693 + value: 62.41250554765521 - type: manhattan_spearman - value: 50.84858327663952 + value: 62.87580558029627 - task: type: STS dataset: @@ -5037,17 +5939,17 @@ model-index: revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson - value: 59.1627744693388 + value: 59.16277512775291 - type: cos_sim_spearman - value: 57.53692924942505 + value: 57.53693422381856 - type: euclidean_pearson - value: 43.86657039278782 + value: 57.85017283427473 - type: euclidean_spearman - value: 45.082440020418424 + value: 57.53697385589326 - type: manhattan_pearson - value: 43.955740479348044 + value: 58.049796184955596 - type: manhattan_spearman - value: 45.15905727160372 + value: 57.76174789162225 - task: type: STS dataset: @@ -5058,17 +5960,17 @@ model-index: revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson - value: 74.42588616006334 + value: 74.42588553600197 - type: cos_sim_spearman - value: 74.25087851075787 + value: 74.25087788257943 - type: euclidean_pearson - value: 63.646746727259774 + value: 73.35436018935222 - type: euclidean_spearman - value: 63.150219043712106 + value: 74.25087694991477 - type: manhattan_pearson - value: 63.5341614083317 + value: 73.33747415771185 - type: manhattan_spearman - value: 63.00883784164611 + value: 74.21504509447377 - task: type: STS dataset: @@ -5079,17 +5981,17 @@ model-index: revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson - value: 75.77242395196524 + value: 75.77242432372144 - type: cos_sim_spearman value: 75.72930700521489 - type: euclidean_pearson - value: 68.76523039736611 + value: 75.6995220623788 - type: euclidean_spearman - value: 67.96962494828459 + value: 75.72930646047212 - type: manhattan_pearson - value: 68.66742487680166 + value: 75.65841087952896 - type: manhattan_spearman - value: 67.89168383123581 + value: 75.69567692328437 - task: type: STS dataset: @@ -5100,17 +6002,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 66.24952916970275 + value: 66.2495297342053 - type: cos_sim_spearman - value: 66.14121993606645 + value: 66.14124319602982 - type: euclidean_pearson - value: 48.49193377121151 + value: 66.49498096178358 - type: euclidean_spearman - value: 48.30443629726529 + value: 66.14121792287747 - type: manhattan_pearson - value: 48.580679507100214 + value: 66.51560623835172 - type: manhattan_spearman - value: 48.163570736145374 + value: 66.05794413582558 - task: type: STS dataset: @@ -5121,17 +6023,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 75.00451698478369 + value: 75.0045186560239 - type: cos_sim_spearman value: 74.96504390762252 - type: euclidean_pearson - value: 71.41544320562012 + value: 74.20988464347049 - type: euclidean_spearman - value: 69.8671968302191 + value: 74.98114602301776 - type: manhattan_pearson - value: 71.51396887529955 + value: 74.37929169860529 - type: manhattan_spearman - value: 70.13646740313014 + value: 75.37049827509504 - task: type: STS dataset: @@ -5142,17 +6044,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 73.88477970895238 + value: 73.88478151514396 - type: cos_sim_spearman value: 74.05322141272103 - type: euclidean_pearson - value: 60.60761818278518 + value: 73.52175483343693 - type: euclidean_spearman - value: 59.33251110095505 + value: 74.05322141272103 - type: manhattan_pearson - value: 60.419868469543594 + value: 73.35875118828287 - type: manhattan_spearman - value: 59.298607116416505 + value: 73.83972625384673 - task: type: STS dataset: @@ -5163,17 +6065,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 75.57014739802696 + value: 75.57014781622605 - type: cos_sim_spearman value: 74.95329129562734 - type: euclidean_pearson - value: 66.04424909946401 + value: 75.5667786729257 - type: euclidean_spearman - value: 65.36290486357399 + value: 74.95329129562734 - type: manhattan_pearson - value: 65.85564903072199 + value: 75.39548673816147 - type: manhattan_spearman - value: 65.1132393036515 + value: 74.89428642503749 - task: type: STS dataset: @@ -5184,17 +6086,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 80.04007186284058 + value: 80.04007129652777 - type: cos_sim_spearman value: 79.94429611477106 - type: euclidean_pearson - value: 73.04121359782312 + value: 79.91583070858822 - type: euclidean_spearman - value: 72.46378547225223 + value: 79.94429611477106 - type: manhattan_pearson - value: 73.20754563807353 + value: 80.14382273152769 - type: manhattan_spearman - value: 72.61008679959097 + value: 80.23862855392836 - task: type: STS dataset: @@ -5205,17 +6107,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 77.28740927858394 + value: 77.28740870194635 - type: cos_sim_spearman value: 77.18286391819586 - type: euclidean_pearson - value: 67.75873608167655 + value: 77.05644328687119 - type: euclidean_spearman - value: 66.81787653005944 + value: 77.18286391819586 - type: manhattan_pearson - value: 67.77279216343489 + value: 77.15625898067294 - type: manhattan_spearman - value: 66.9579776982823 + value: 77.03165154316278 - task: type: STS dataset: @@ -5226,17 +6128,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 72.99292955338515 + value: 72.99293002371301 - type: cos_sim_spearman value: 72.24657859872468 - type: euclidean_pearson - value: 63.52202589317903 + value: 73.38839879755461 - type: euclidean_spearman - value: 62.33443239002958 + value: 72.24657859872468 - type: manhattan_pearson - value: 63.769212052975476 + value: 73.6627728800822 - type: manhattan_spearman - value: 62.81347262019862 + value: 72.70893449698669 - task: type: STS dataset: @@ -5247,17 +6149,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 81.37213847952495 + value: 81.37213723705916 - type: cos_sim_spearman value: 80.64548512701263 - type: euclidean_pearson - value: 78.20509452005497 + value: 80.94992193351284 - type: euclidean_spearman - value: 76.92821412749807 + value: 80.64484963200427 - type: manhattan_pearson - value: 78.18187623856416 + value: 80.92246813841794 - type: manhattan_spearman - value: 76.80662828217807 + value: 80.68860823161657 - task: type: STS dataset: @@ -5268,17 +6170,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 77.54059838849403 + value: 77.54059604962391 - type: cos_sim_spearman value: 77.19559169700682 - type: euclidean_pearson - value: 65.48086288727644 + value: 77.32739821317861 - type: euclidean_spearman - value: 65.00387848487095 + value: 77.19559169700682 - type: manhattan_pearson - value: 65.39875192421043 + value: 77.29224328831437 - type: manhattan_spearman - value: 64.99073212282424 + value: 77.24394878313191 - task: type: STS dataset: @@ -5289,17 +6191,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 79.06396980015494 + value: 79.06397062195414 - type: cos_sim_spearman value: 78.66694637555244 - type: euclidean_pearson - value: 69.77559635500967 + value: 79.34923290885872 - type: euclidean_spearman - value: 69.6548076752796 + value: 78.66694637555244 - type: manhattan_pearson - value: 69.80486003899448 + value: 79.50802161625809 - type: manhattan_spearman - value: 69.64277606323098 + value: 78.79195213396169 - task: type: STS dataset: @@ -5310,17 +6212,17 @@ model-index: revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson - value: 78.66045887460483 + value: 78.66045829245238 - type: cos_sim_spearman value: 78.14055373851183 - type: euclidean_pearson - value: 69.24649434854432 + value: 78.94489279300518 - type: euclidean_spearman - value: 68.92768315926817 + value: 78.14055373851183 - type: manhattan_pearson - value: 69.53186552758453 + value: 79.33473165536323 - type: manhattan_spearman - value: 69.1888421760678 + value: 78.5783429705299 - task: type: STS dataset: @@ -5331,17 +6233,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 36.63454695072987 + value: 36.63454535818336 - type: cos_sim_spearman value: 47.12016162570126 - type: euclidean_pearson - value: 40.706330494343604 + value: 39.07268779927362 - type: euclidean_spearman - value: 48.865006150948616 + value: 47.12016162570126 - type: manhattan_pearson - value: 45.099280138151926 + value: 41.723119770725944 - type: manhattan_spearman - value: 51.15098931364965 + value: 47.90334362422989 - task: type: STS dataset: @@ -5352,17 +6254,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 13.32554927123781 + value: 13.325547358617957 - type: cos_sim_spearman value: 24.094051740693416 - type: euclidean_pearson - value: 5.733247674182589 + value: 10.39110006005262 - type: euclidean_spearman - value: 17.32765054587116 + value: 24.094051740693416 - type: manhattan_pearson - value: 7.85068670554767 + value: 12.4380555005162 - type: manhattan_spearman - value: 19.003823576388488 + value: 25.176800279885715 - task: type: STS dataset: @@ -5373,17 +6275,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 41.212816807176836 + value: 41.21281570342249 - type: cos_sim_spearman value: 55.397885077207974 - type: euclidean_pearson - value: 44.32687000784094 + value: 43.96150945976646 - type: euclidean_spearman - value: 54.40126826356849 + value: 55.397885077207974 - type: manhattan_pearson - value: 49.72970710546519 + value: 49.58812224529121 - type: manhattan_spearman - value: 56.49113106101981 + value: 55.35874879475974 - task: type: STS dataset: @@ -5394,17 +6296,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 5.985016492310366 + value: 5.985012243744998 - type: cos_sim_spearman value: 25.307464943919012 - type: euclidean_pearson - value: -6.568128940119214 + value: -4.080537702499046 - type: euclidean_spearman - value: 23.37422025614559 + value: 25.307464943919012 - type: manhattan_pearson - value: -4.99967062376341 + value: -2.5058642304196543 - type: manhattan_spearman - value: 25.00987603568494 + value: 26.751588484373233 - task: type: STS dataset: @@ -5415,17 +6317,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 34.44666733247214 + value: 34.44666578772084 - type: cos_sim_spearman value: 46.45977141800899 - type: euclidean_pearson - value: 38.168335484005496 + value: 38.78305544036559 - type: euclidean_spearman - value: 45.87203585565584 + value: 46.45977141800899 - type: manhattan_pearson - value: 45.96851222581045 + value: 46.45101297876112 - type: manhattan_spearman - value: 50.72243559635815 + value: 50.642972694093814 - task: type: STS dataset: @@ -5436,17 +6338,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 28.095330260570044 + value: 28.095327083873055 - type: cos_sim_spearman value: 40.24741745875892 - type: euclidean_pearson - value: 34.298302094447 + value: 29.141496784653892 - type: euclidean_spearman - value: 41.75099510117058 + value: 40.24741745875892 - type: manhattan_pearson - value: 36.822574344860016 + value: 32.013290716034064 - type: manhattan_spearman - value: 43.24173881526762 + value: 40.85454084311211 - task: type: STS dataset: @@ -5457,17 +6359,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 27.467875570822507 + value: 27.46788309503312 - type: cos_sim_spearman value: 43.57385391855994 - type: euclidean_pearson - value: 22.17414485325322 + value: 24.558349674326177 - type: euclidean_spearman - value: 39.95656416250951 + value: 43.57385391855994 - type: manhattan_pearson - value: 26.066273487373664 + value: 28.974505207055866 - type: manhattan_spearman - value: 40.14230396654245 + value: 44.111553205713 - task: type: STS dataset: @@ -5478,17 +6380,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 34.87842153404196 + value: 34.87841073990563 - type: cos_sim_spearman value: 52.8221686505807 - type: euclidean_pearson - value: 35.93221146007856 + value: 38.36114580544504 - type: euclidean_spearman - value: 51.489361135954105 + value: 52.8221686505807 - type: manhattan_pearson - value: 44.030913421863026 + value: 46.69329448756753 - type: manhattan_spearman - value: 52.999521693608465 + value: 53.9140781097337 - task: type: STS dataset: @@ -5499,17 +6401,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 49.999270334861315 + value: 49.999267528357 - type: cos_sim_spearman value: 61.71837669697145 - type: euclidean_pearson - value: 49.955296540972824 + value: 53.578476744372274 - type: euclidean_spearman - value: 56.505586159244515 + value: 61.71837669697145 - type: manhattan_pearson - value: 52.49957702118715 + value: 56.410294227490795 - type: manhattan_spearman - value: 57.12582682664643 + value: 60.684457655864875 - task: type: STS dataset: @@ -5520,17 +6422,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 22.43564766265908 + value: 22.43564137760586 - type: cos_sim_spearman value: 34.28346144104183 - type: euclidean_pearson - value: 33.017091607053786 + value: 27.41326011184764 - type: euclidean_spearman - value: 37.60239300835095 + value: 34.28346144104183 - type: manhattan_pearson - value: 43.842762856035904 + value: 35.62923154232163 - type: manhattan_spearman - value: 44.71536370367842 + value: 37.937151135297185 - task: type: STS dataset: @@ -5541,17 +6443,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 44.34071373662986 + value: 44.34071611983998 - type: cos_sim_spearman value: 57.823185616169646 - type: euclidean_pearson - value: 53.672221309748835 + value: 49.29310650157244 - type: euclidean_spearman - value: 62.001696407713126 + value: 57.823185616169646 - type: manhattan_pearson - value: 61.30617811516088 + value: 55.93298736518848 - type: manhattan_spearman - value: 63.97035045686644 + value: 58.57556581684834 - task: type: STS dataset: @@ -5562,17 +6464,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 56.07027264854201 + value: 56.07027840344927 - type: cos_sim_spearman value: 62.20158260763411 - type: euclidean_pearson - value: 55.89068916951512 + value: 55.887969718543616 - type: euclidean_spearman - value: 61.46687669950822 + value: 62.20158260763411 - type: manhattan_pearson - value: 55.82045134105482 + value: 56.081533365738444 - type: manhattan_spearman - value: 61.097021240849394 + value: 62.018651361750685 - task: type: STS dataset: @@ -5583,17 +6485,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 41.418158049627344 + value: 41.41816324477061 - type: cos_sim_spearman value: 44.71684955996943 - type: euclidean_pearson - value: 44.09873868592676 + value: 42.74585025834968 - type: euclidean_spearman - value: 48.582169034980765 + value: 44.71684955996943 - type: manhattan_pearson - value: 51.11307812290116 + value: 47.992481632815256 - type: manhattan_spearman - value: 51.613996439908796 + value: 46.18587933349126 - task: type: STS dataset: @@ -5604,17 +6506,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 38.89141661170763 + value: 38.89140730917917 - type: cos_sim_spearman value: 49.18633779347391 - type: euclidean_pearson - value: 48.37473555026282 + value: 43.27605428753535 - type: euclidean_spearman - value: 54.17536451762477 + value: 49.18633779347391 - type: manhattan_pearson - value: 55.06464763414177 + value: 48.22046568809415 - type: manhattan_spearman - value: 55.27394644455171 + value: 49.248416391249464 - task: type: STS dataset: @@ -5625,17 +6527,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 40.31621370101309 + value: 40.31620568726327 - type: cos_sim_spearman value: 49.13034440774138 - type: euclidean_pearson - value: 46.55326804225437 + value: 43.95169508285692 - type: euclidean_spearman - value: 50.04387120070582 + value: 49.13034440774138 - type: manhattan_pearson - value: 51.108871970953615 + value: 48.84250981398146 - type: manhattan_spearman - value: 50.77822527742335 + value: 49.54216339903405 - task: type: STS dataset: @@ -5646,17 +6548,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 27.07459941263371 + value: 27.074582378144058 - type: cos_sim_spearman value: 41.29498619968451 - type: euclidean_pearson - value: 28.81148557875536 + value: 28.993986097276505 - type: euclidean_spearman - value: 44.23270186092313 + value: 41.29498619968451 - type: manhattan_pearson - value: 33.37331199208485 + value: 32.079813951133254 - type: manhattan_spearman - value: 44.702014347511174 + value: 43.664111732941464 - task: type: STS dataset: @@ -5667,17 +6569,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 6.864350141604963 + value: 6.864334110072116 - type: cos_sim_spearman value: 25.805458732687914 - type: euclidean_pearson - value: 22.41182782328486 + value: 11.435920047618103 - type: euclidean_spearman - value: 41.47965741399835 + value: 25.805458732687914 - type: manhattan_pearson - value: 27.52235896097151 + value: 15.036308569899552 - type: manhattan_spearman - value: 45.11336162695441 + value: 25.405135387192757 - task: type: STS dataset: @@ -5688,17 +6590,17 @@ model-index: revision: eea2b4fe26a775864c896887d910b76a8098ad3f metrics: - type: cos_sim_pearson - value: 65.4403182219975 + value: 65.44029549925597 - type: cos_sim_spearman value: 61.97797868009122 - type: euclidean_pearson - value: 57.9607330049556 + value: 65.92740669959876 - type: euclidean_spearman - value: 50.709255283710995 + value: 61.97797868009122 - type: manhattan_pearson - value: 61.3956353319538 + value: 70.29575044091207 - type: manhattan_spearman - value: 61.97797868009122 + value: 73.24670207647144 - task: type: STS dataset: @@ -5709,17 +6611,17 @@ model-index: revision: 0cde68302b3541bb8b3c340dc0644b0b745b3dc0 metrics: - type: cos_sim_pearson - value: 51.354132781205294 + value: 51.35413149349556 - type: cos_sim_spearman - value: 50.17494133468151 + value: 50.175051356729924 - type: euclidean_pearson - value: 38.11014000059295 + value: 53.12039152785364 - type: euclidean_spearman - value: 37.5997050693584 + value: 50.174289111089685 - type: manhattan_pearson - value: 37.99036693507327 + value: 53.0731746793555 - type: manhattan_spearman - value: 37.584133861146974 + value: 50.15176393928403 - task: type: STS dataset: @@ -5730,17 +6632,17 @@ model-index: revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson - value: 67.84222997484147 + value: 67.84222983023291 - type: cos_sim_spearman value: 67.39086924655895 - type: euclidean_pearson - value: 51.87216665821589 + value: 67.3393327127967 - type: euclidean_spearman - value: 51.309915218441695 + value: 67.39088047106472 - type: manhattan_pearson - value: 51.871943884893454 + value: 67.40316731822271 - type: manhattan_spearman - value: 51.271356979504375 + value: 67.49067800994015 - task: type: Classification dataset: @@ -5751,11 +6653,11 @@ model-index: revision: 1de08520a7b361e92ffa2a2201ebd41942c54675 metrics: - type: accuracy - value: 50.68359375 + value: 50.62988281250001 - type: ap - value: 50.348173771768124 + value: 50.32274824114816 - type: f1 - value: 50.38855675524828 + value: 50.37741703766756 - task: type: Classification dataset: @@ -5766,11 +6668,11 @@ model-index: revision: 237111a078ad5a834a55c57803d40bbe410ed03b metrics: - type: accuracy - value: 50.9033203125 + value: 51.181640625 - type: ap - value: 50.464534818390305 + value: 50.60884394099696 - type: f1 - value: 50.12338348445107 + value: 50.866988720930415 - task: type: Classification dataset: @@ -5781,11 +6683,11 @@ model-index: revision: 9d9a2a4092ed3cacf0744592f6d2f32ab8ef4c0b metrics: - type: accuracy - value: 50.7568359375 + value: 50.9375 - type: ap - value: 50.38550393534486 + value: 50.47969135089731 - type: f1 - value: 50.19852110629762 + value: 50.62913552324756 - task: type: Classification dataset: @@ -5796,11 +6698,11 @@ model-index: revision: 1b48e3dcb02872335ff985ff938a054a4ed99008 metrics: - type: accuracy - value: 50.9619140625 + value: 51.1474609375 - type: ap - value: 50.494690837095156 + value: 50.5894187272385 - type: f1 - value: 50.26727387729569 + value: 50.901812392367916 - task: type: Reranking dataset: @@ -5883,6 +6785,75 @@ model-index: value: 35.693999999999996 - type: recall_at_5 value: 40.944 + - task: + type: Retrieval + dataset: + type: scifact-pl + name: MTEB SciFact-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 21.706 + - type: map_at_10 + value: 28.333000000000002 + - type: map_at_100 + value: 29.364 + - type: map_at_1000 + value: 29.451 + - type: map_at_3 + value: 26.112999999999996 + - type: map_at_5 + value: 27.502 + - type: mrr_at_1 + value: 23.0 + - type: mrr_at_10 + value: 29.555999999999997 + - type: mrr_at_100 + value: 30.536 + - type: mrr_at_1000 + value: 30.606 + - type: mrr_at_3 + value: 27.333000000000002 + - type: mrr_at_5 + value: 28.717 + - type: ndcg_at_1 + value: 23.0 + - type: ndcg_at_10 + value: 32.238 + - type: ndcg_at_100 + value: 37.785999999999994 + - type: ndcg_at_1000 + value: 40.266999999999996 + - type: ndcg_at_3 + value: 27.961000000000002 + - type: ndcg_at_5 + value: 30.322 + - type: precision_at_1 + value: 23.0 + - type: precision_at_10 + value: 4.7669999999999995 + - type: precision_at_100 + value: 0.787 + - type: precision_at_1000 + value: 0.10200000000000001 + - type: precision_at_3 + value: 11.444 + - type: precision_at_5 + value: 8.200000000000001 + - type: recall_at_1 + value: 21.706 + - type: recall_at_10 + value: 43.206 + - type: recall_at_100 + value: 69.678 + - type: recall_at_1000 + value: 89.333 + - type: recall_at_3 + value: 31.900000000000002 + - type: recall_at_5 + value: 37.594 - task: type: PairClassification dataset: @@ -5903,41 +6874,41 @@ model-index: - type: cos_sim_recall value: 68.4 - type: dot_accuracy - value: 99.19108910891089 + value: 99.5 - type: dot_ap - value: 49.25491405967686 + value: 77.07584309978081 - type: dot_f1 - value: 49.716932578486876 + value: 71.8864950078823 - type: dot_precision - value: 51.21951219512195 + value: 75.74750830564784 - type: dot_recall - value: 48.3 + value: 68.4 - type: euclidean_accuracy - value: 99.19009900990099 + value: 99.5 - type: euclidean_ap - value: 42.03570656308142 + value: 77.07584309978081 - type: euclidean_f1 - value: 44.82153306026916 + value: 71.8864950078823 - type: euclidean_precision - value: 54.01974612129761 + value: 75.74750830564784 - type: euclidean_recall - value: 38.3 + value: 68.4 - type: manhattan_accuracy - value: 99.19207920792078 + value: 99.50594059405941 - type: manhattan_ap - value: 42.109436522707014 + value: 77.41658577240027 - type: manhattan_f1 - value: 44.79905437352246 + value: 71.91374663072777 - type: manhattan_precision - value: 54.76878612716764 + value: 78.01169590643275 - type: manhattan_recall - value: 37.9 + value: 66.7 - type: max_accuracy - value: 99.5 + value: 99.50594059405941 - type: max_ap - value: 77.07584309978081 + value: 77.41658577240027 - type: max_f1 - value: 71.8864950078823 + value: 71.91374663072777 - task: type: Clustering dataset: @@ -5948,7 +6919,7 @@ model-index: revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure - value: 37.40985053432638 + value: 46.32521494308228 - task: type: Clustering dataset: @@ -5959,7 +6930,7 @@ model-index: revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure - value: 19.657671371166966 + value: 20.573273825125266 - task: type: Reranking dataset: @@ -5983,13 +6954,13 @@ model-index: revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson - value: 29.305333790118766 + value: 29.305330424238836 - type: cos_sim_spearman value: 30.556621737388685 - type: dot_pearson - value: 30.309505984206115 + value: 29.30533056265583 - type: dot_spearman - value: 31.302092660260872 + value: 30.556621737388685 - task: type: Classification dataset: @@ -6000,9 +6971,9 @@ model-index: revision: 3c62f26bafdc4c4e1c16401ad4b32f0a94b46612 metrics: - type: accuracy - value: 66.8701171875 + value: 68.4716796875 - type: f1 - value: 54.75017096649799 + value: 59.865730786092364 - task: type: Reranking dataset: @@ -6095,9 +7066,9 @@ model-index: revision: 317f262bf1e6126357bbe89e875451e4b0938fe4 metrics: - type: accuracy - value: 37.254 + value: 40.946 - type: f1 - value: 36.23675255530671 + value: 39.56517169731474 - task: type: Retrieval dataset: @@ -6167,6 +7138,75 @@ model-index: value: 0.28200000000000003 - type: recall_at_5 value: 0.379 + - task: + type: Retrieval + dataset: + type: trec-covid-pl + name: MTEB TRECCOVID-PL + config: default + split: test + revision: None + metrics: + - type: map_at_1 + value: 0.124 + - type: map_at_10 + value: 0.45199999999999996 + - type: map_at_100 + value: 0.874 + - type: map_at_1000 + value: 1.1039999999999999 + - type: map_at_3 + value: 0.253 + - type: map_at_5 + value: 0.32299999999999995 + - type: mrr_at_1 + value: 36.0 + - type: mrr_at_10 + value: 47.56 + - type: mrr_at_100 + value: 48.532 + - type: mrr_at_1000 + value: 48.579 + - type: mrr_at_3 + value: 45.0 + - type: mrr_at_5 + value: 45.5 + - type: ndcg_at_1 + value: 34.0 + - type: ndcg_at_10 + value: 24.529 + - type: ndcg_at_100 + value: 10.427 + - type: ndcg_at_1000 + value: 6.457 + - type: ndcg_at_3 + value: 31.173000000000002 + - type: ndcg_at_5 + value: 27.738000000000003 + - type: precision_at_1 + value: 38.0 + - type: precision_at_10 + value: 25.4 + - type: precision_at_100 + value: 8.88 + - type: precision_at_1000 + value: 2.2159999999999997 + - type: precision_at_3 + value: 34.666999999999994 + - type: precision_at_5 + value: 29.2 + - type: recall_at_1 + value: 0.124 + - type: recall_at_10 + value: 0.618 + - type: recall_at_100 + value: 1.9349999999999998 + - type: recall_at_1000 + value: 4.808 + - type: recall_at_3 + value: 0.28300000000000003 + - type: recall_at_5 + value: 0.382 - task: type: BitextMining dataset: @@ -6519,7 +7559,7 @@ model-index: - type: accuracy value: 70.47619047619048 - type: f1 - value: 66.63032734461308 + value: 66.63032734461306 - type: precision value: 65.46459191863879 - type: recall @@ -8081,7 +9121,7 @@ model-index: revision: 5c59e41555244b7e45c9a6be2d720ab4bafae558 metrics: - type: v_measure - value: 19.988360713728564 + value: 21.827519839402644 - task: type: Clustering dataset: @@ -8092,7 +9132,7 @@ model-index: revision: 6cddbe003f12b9b140aec477b583ac4191f01786 metrics: - type: v_measure - value: 25.49952010397176 + value: 27.160188241713684 - task: type: Clustering dataset: @@ -8103,7 +9143,7 @@ model-index: revision: 5798586b105c0434e4f0fe5e767abe619442cf93 metrics: - type: v_measure - value: 32.012653950111556 + value: 38.54459276932986 - task: type: Clustering dataset: @@ -8114,7 +9154,7 @@ model-index: revision: 8a8b2caeda43f39e13c4bc5bea0f8a667896e10d metrics: - type: v_measure - value: 42.08914091890925 + value: 43.4460576234314 - task: type: Retrieval dataset: @@ -8194,11 +9234,11 @@ model-index: revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy - value: 63.5394 + value: 67.28359999999999 - type: ap - value: 11.440330234311777 + value: 12.424592214862038 - type: f1 - value: 48.937405112008854 + value: 51.53630450055703 - task: type: Classification dataset: @@ -8209,9 +9249,9 @@ model-index: revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy - value: 55.16694963214488 + value: 56.23372948500284 - type: f1 - value: 55.275387066931124 + value: 56.440924587214234 - task: type: Clustering dataset: @@ -8222,7 +9262,7 @@ model-index: revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure - value: 19.628551067284956 + value: 24.410059815620116 - task: type: PairClassification dataset: @@ -8235,7 +9275,7 @@ model-index: - type: cos_sim_accuracy value: 80.3302139834297 - type: cos_sim_ap - value: 53.577244820707605 + value: 53.57723069745093 - type: cos_sim_f1 value: 51.58639580004565 - type: cos_sim_precision @@ -8243,39 +9283,39 @@ model-index: - type: cos_sim_recall value: 59.63060686015831 - type: dot_accuracy - value: 80.14543720569827 + value: 80.3302139834297 - type: dot_ap - value: 52.0875752603294 + value: 53.57723006705641 - type: dot_f1 - value: 51.38086062941555 + value: 51.58639580004565 - type: dot_precision - value: 43.22766570605187 + value: 45.45454545454545 - type: dot_recall - value: 63.3245382585752 + value: 59.63060686015831 - type: euclidean_accuracy - value: 78.82815759670979 + value: 80.3302139834297 - type: euclidean_ap - value: 42.100001806860824 + value: 53.57723050286929 - type: euclidean_f1 - value: 42.769230769230774 + value: 51.58639580004565 - type: euclidean_precision - value: 34.98322147651007 + value: 45.45454545454545 - type: euclidean_recall - value: 55.01319261213721 + value: 59.63060686015831 - type: manhattan_accuracy - value: 78.82815759670979 + value: 80.31233235977827 - type: manhattan_ap - value: 41.936649509973165 + value: 53.44943961562638 - type: manhattan_f1 - value: 42.57720324202319 + value: 51.24183006535947 - type: manhattan_precision - value: 34.832969615578314 + value: 43.63636363636363 - type: manhattan_recall - value: 54.74934036939314 + value: 62.05804749340369 - type: max_accuracy value: 80.3302139834297 - type: max_ap - value: 53.577244820707605 + value: 53.57723069745093 - type: max_f1 value: 51.58639580004565 - task: @@ -8290,7 +9330,7 @@ model-index: - type: cos_sim_accuracy value: 87.45876508712695 - type: cos_sim_ap - value: 83.53208334948403 + value: 83.5320716566614 - type: cos_sim_f1 value: 75.54560716284276 - type: cos_sim_precision @@ -8298,39 +9338,39 @@ model-index: - type: cos_sim_recall value: 77.95657530027718 - type: dot_accuracy - value: 85.64054798773626 + value: 87.45876508712695 - type: dot_ap - value: 77.96456929342345 + value: 83.53209944887666 - type: dot_f1 - value: 72.09775967413442 + value: 75.54560716284276 - type: dot_precision - value: 67.26448429895326 + value: 73.27929362379678 - type: dot_recall - value: 77.6793963658762 + value: 77.95657530027718 - type: euclidean_accuracy - value: 84.78480226646485 + value: 87.45876508712695 - type: euclidean_ap - value: 75.64618087898923 + value: 83.53205938307582 - type: euclidean_f1 - value: 67.1075581395349 + value: 75.54560716284276 - type: euclidean_precision - value: 63.54252683732452 + value: 73.27929362379678 - type: euclidean_recall - value: 71.0963966738528 + value: 77.95657530027718 - type: manhattan_accuracy - value: 84.72658827182055 + value: 87.52280048123569 - type: manhattan_ap - value: 75.51009726264691 + value: 83.4884324728773 - type: manhattan_f1 - value: 67.00128311570685 + value: 75.43366677906411 - type: manhattan_precision - value: 65.70688378978534 + value: 73.46566445303948 - type: manhattan_recall - value: 68.34770557437635 + value: 77.51000923929782 - type: max_accuracy - value: 87.45876508712695 + value: 87.52280048123569 - type: max_ap - value: 83.53208334948403 + value: 83.53209944887666 - type: max_f1 value: 75.54560716284276 - task: @@ -8412,11 +9452,11 @@ model-index: revision: 339287def212450dcaa9df8c22bf93e9980c7023 metrics: - type: accuracy - value: 70.44 + value: 76.12 - type: ap - value: 49.70788956752899 + value: 54.1619589378045 - type: f1 - value: 69.57867775339233 + value: 74.32372858884229 - task: type: Clustering dataset: @@ -8427,7 +9467,76 @@ model-index: revision: ddc9ee9242fa65332597f70e967ecc38b9d734fa metrics: - type: v_measure - value: 48.038657353672534 + value: 50.71744674029636 + - task: + type: Retrieval + dataset: + type: jinaai/xmarket_de + name: MTEB XMarketDE + config: default + split: test + revision: 2336818db4c06570fcdf263e1bcb9993b786f67a + metrics: + - type: map_at_1 + value: 0.182 + - type: map_at_10 + value: 0.266 + - type: map_at_100 + value: 0.295 + - type: map_at_1000 + value: 0.313 + - type: map_at_3 + value: 0.232 + - type: map_at_5 + value: 0.23800000000000002 + - type: mrr_at_1 + value: 1.3379999999999999 + - type: mrr_at_10 + value: 1.918 + - type: mrr_at_100 + value: 2.051 + - type: mrr_at_1000 + value: 2.084 + - type: mrr_at_3 + value: 1.7049999999999998 + - type: mrr_at_5 + value: 1.791 + - type: ndcg_at_1 + value: 1.3379999999999999 + - type: ndcg_at_10 + value: 0.859 + - type: ndcg_at_100 + value: 0.8500000000000001 + - type: ndcg_at_1000 + value: 1.345 + - type: ndcg_at_3 + value: 1.032 + - type: ndcg_at_5 + value: 0.918 + - type: precision_at_1 + value: 1.3379999999999999 + - type: precision_at_10 + value: 0.528 + - type: precision_at_100 + value: 0.22699999999999998 + - type: precision_at_1000 + value: 0.132 + - type: precision_at_3 + value: 0.8829999999999999 + - type: precision_at_5 + value: 0.6890000000000001 + - type: recall_at_1 + value: 0.182 + - type: recall_at_10 + value: 0.51 + - type: recall_at_100 + value: 1.2229999999999999 + - type: recall_at_1000 + value: 4.183 + - type: recall_at_3 + value: 0.292 + - type: recall_at_5 + value: 0.315 --- # SONAR