diff --git a/.eval_results/AILACasedocs.yaml b/.eval_results/AILACasedocs.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c051dd31d80d53c70332c68543b05ac838e531db --- /dev/null +++ b/.eval_results/AILACasedocs.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/AILA_casedocs + revision: 4106e6bcc72e0698d714ea8b101355e3e238431a + task_id: AILACasedocs_default_test + notes: Created by mteb + value: 0.27837 +- dataset: + id: mteb/AILA_casedocs + revision: 4106e6bcc72e0698d714ea8b101355e3e238431a + task_id: AILACasedocs + notes: Created by mteb + value: 0.27837 diff --git a/.eval_results/AILAStatutes.yaml b/.eval_results/AILAStatutes.yaml new file mode 100644 index 0000000000000000000000000000000000000000..87683b8e68338fe1e6b59e78b0815b3f74ae027f --- /dev/null +++ b/.eval_results/AILAStatutes.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/AILA_statutes + revision: ebfcd844eadd3d667efa3c57fc5c8c87f5c2867e + task_id: AILAStatutes_default_test + notes: Created by mteb + value: 0.21618 +- dataset: + id: mteb/AILA_statutes + revision: ebfcd844eadd3d667efa3c57fc5c8c87f5c2867e + task_id: AILAStatutes + notes: Created by mteb + value: 0.21618 diff --git a/.eval_results/AppsRetrieval.yaml b/.eval_results/AppsRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..38a44da22f1fd6d74006dbec9ec71e64fb377e7f --- /dev/null +++ b/.eval_results/AppsRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: CoIR-Retrieval/apps + revision: f22508f96b7a36c2415181ed8bb76f76e04ae2d5 + task_id: AppsRetrieval_default_test + notes: Created by mteb + value: 0.04764 +- dataset: + id: CoIR-Retrieval/apps + revision: f22508f96b7a36c2415181ed8bb76f76e04ae2d5 + task_id: AppsRetrieval + notes: Created by mteb + value: 0.04764 diff --git a/.eval_results/ArguAna.yaml b/.eval_results/ArguAna.yaml new file mode 100644 index 0000000000000000000000000000000000000000..10d9c387b2d752c13a839b93fc1a20639b3e15c4 --- /dev/null +++ b/.eval_results/ArguAna.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/arguana + revision: c22ab2a51041ffd869aaddef7af8d8215647e41a + task_id: ArguAna_default_test + notes: Created by mteb + value: 0.49276 +- dataset: + id: mteb/arguana + revision: c22ab2a51041ffd869aaddef7af8d8215647e41a + task_id: ArguAna + notes: Created by mteb + value: 0.49276 diff --git a/.eval_results/CQADupstackAndroidRetrieval.yaml b/.eval_results/CQADupstackAndroidRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..09fad018f412f0e81a3132a429eec8d14a0276c8 --- /dev/null +++ b/.eval_results/CQADupstackAndroidRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/CQADupstackAndroidRetrieval + revision: 9be4c0e46342e8e3aff577a89b9a1ec9bc6b4af3 + task_id: CQADupstackAndroidRetrieval_default_test + notes: Created by mteb + value: 0.39693 +- dataset: + id: mteb/CQADupstackAndroidRetrieval + revision: 9be4c0e46342e8e3aff577a89b9a1ec9bc6b4af3 + task_id: CQADupstackAndroidRetrieval + notes: Created by mteb + value: 0.39693 diff --git a/.eval_results/CQADupstackEnglishRetrieval.yaml b/.eval_results/CQADupstackEnglishRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5fae500cf0a2fe370d055d96a01b4db60373e1f3 --- /dev/null +++ b/.eval_results/CQADupstackEnglishRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-english + revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 + task_id: CQADupstackEnglishRetrieval_default_test + notes: Created by mteb + value: 0.34746 +- dataset: + id: mteb/cqadupstack-english + revision: ad9991cb51e31e31e430383c75ffb2885547b5f0 + task_id: CQADupstackEnglishRetrieval + notes: Created by mteb + value: 0.34746 diff --git a/.eval_results/CQADupstackGamingRetrieval.yaml b/.eval_results/CQADupstackGamingRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dd7e7e5dd51ee497f2a369a1da819f5e115af800 --- /dev/null +++ b/.eval_results/CQADupstackGamingRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-gaming + revision: 4885aa143210c98657558c04aaf3dc47cfb54340 + task_id: CQADupstackGamingRetrieval_default_test + notes: Created by mteb + value: 0.48471 +- dataset: + id: mteb/cqadupstack-gaming + revision: 4885aa143210c98657558c04aaf3dc47cfb54340 + task_id: CQADupstackGamingRetrieval + notes: Created by mteb + value: 0.48471 diff --git a/.eval_results/CQADupstackGisRetrieval.yaml b/.eval_results/CQADupstackGisRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..39d42178863262960f86c78883beaa8568154a24 --- /dev/null +++ b/.eval_results/CQADupstackGisRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-gis + revision: 5003b3064772da1887988e05400cf3806fe491f2 + task_id: CQADupstackGisRetrieval_default_test + notes: Created by mteb + value: 0.3083 +- dataset: + id: mteb/cqadupstack-gis + revision: 5003b3064772da1887988e05400cf3806fe491f2 + task_id: CQADupstackGisRetrieval + notes: Created by mteb + value: 0.3083 diff --git a/.eval_results/CQADupstackMathematicaRetrieval.yaml b/.eval_results/CQADupstackMathematicaRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cbc1b01085393ba8425817ed97a65336590e35d1 --- /dev/null +++ b/.eval_results/CQADupstackMathematicaRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-mathematica + revision: 90fceea13679c63fe563ded68f3b6f06e50061de + task_id: CQADupstackMathematicaRetrieval_default_test + notes: Created by mteb + value: 0.22017 +- dataset: + id: mteb/cqadupstack-mathematica + revision: 90fceea13679c63fe563ded68f3b6f06e50061de + task_id: CQADupstackMathematicaRetrieval + notes: Created by mteb + value: 0.22017 diff --git a/.eval_results/CQADupstackPhysicsRetrieval.yaml b/.eval_results/CQADupstackPhysicsRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bbd8907d2589db8a3a8c327fba0ea40c527eff0b --- /dev/null +++ b/.eval_results/CQADupstackPhysicsRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-physics + revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 + task_id: CQADupstackPhysicsRetrieval_default_test + notes: Created by mteb + value: 0.34926 +- dataset: + id: mteb/cqadupstack-physics + revision: 79531abbd1fb92d06c6d6315a0cbbbf5bb247ea4 + task_id: CQADupstackPhysicsRetrieval + notes: Created by mteb + value: 0.34926 diff --git a/.eval_results/CQADupstackProgrammersRetrieval.yaml b/.eval_results/CQADupstackProgrammersRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..56575860b1349ee04f6ffec1b605dac39dd9e035 --- /dev/null +++ b/.eval_results/CQADupstackProgrammersRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-programmers + revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 + task_id: CQADupstackProgrammersRetrieval_default_test + notes: Created by mteb + value: 0.298 +- dataset: + id: mteb/cqadupstack-programmers + revision: 6184bc1440d2dbc7612be22b50686b8826d22b32 + task_id: CQADupstackProgrammersRetrieval + notes: Created by mteb + value: 0.298 diff --git a/.eval_results/CQADupstackRetrieval.yaml b/.eval_results/CQADupstackRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..680f53e4b9dbfecfdf11dc20eeb97d62dd28db4d --- /dev/null +++ b/.eval_results/CQADupstackRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: aggregate tasks do not have a path + revision: '1' + task_id: CQADupstackRetrieval_default_test + notes: Created by mteb + value: 0.318642 +- dataset: + id: aggregate tasks do not have a path + revision: '1' + task_id: CQADupstackRetrieval + notes: Created by mteb + value: 0.318642 diff --git a/.eval_results/CQADupstackStatsRetrieval.yaml b/.eval_results/CQADupstackStatsRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e47ab32778c45dd31b48223247a4bd12de00b047 --- /dev/null +++ b/.eval_results/CQADupstackStatsRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-stats + revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a + task_id: CQADupstackStatsRetrieval_default_test + notes: Created by mteb + value: 0.29019 +- dataset: + id: mteb/cqadupstack-stats + revision: 65ac3a16b8e91f9cee4c9828cc7c335575432a2a + task_id: CQADupstackStatsRetrieval + notes: Created by mteb + value: 0.29019 diff --git a/.eval_results/CQADupstackTexRetrieval.yaml b/.eval_results/CQADupstackTexRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..772741d25d8804f98eeda8b9d034faa3fc9250af --- /dev/null +++ b/.eval_results/CQADupstackTexRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-tex + revision: 46989137a86843e03a6195de44b09deda022eec7 + task_id: CQADupstackTexRetrieval_default_test + notes: Created by mteb + value: 0.24397 +- dataset: + id: mteb/cqadupstack-tex + revision: 46989137a86843e03a6195de44b09deda022eec7 + task_id: CQADupstackTexRetrieval + notes: Created by mteb + value: 0.24397 diff --git a/.eval_results/CQADupstackUnixRetrieval.yaml b/.eval_results/CQADupstackUnixRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..da9d1c4180c14fa0e26ebd716ddc19d4dcda66ed --- /dev/null +++ b/.eval_results/CQADupstackUnixRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-unix + revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 + task_id: CQADupstackUnixRetrieval_default_test + notes: Created by mteb + value: 0.29165 +- dataset: + id: mteb/cqadupstack-unix + revision: 6c6430d3a6d36f8d2a829195bc5dc94d7e063e53 + task_id: CQADupstackUnixRetrieval + notes: Created by mteb + value: 0.29165 diff --git a/.eval_results/CQADupstackWebmastersRetrieval.yaml b/.eval_results/CQADupstackWebmastersRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..29900b3edcda6e98db1da3f338a769924387b65c --- /dev/null +++ b/.eval_results/CQADupstackWebmastersRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-webmasters + revision: 160c094312a0e1facb97e55eeddb698c0abe3571 + task_id: CQADupstackWebmastersRetrieval_default_test + notes: Created by mteb + value: 0.31381 +- dataset: + id: mteb/cqadupstack-webmasters + revision: 160c094312a0e1facb97e55eeddb698c0abe3571 + task_id: CQADupstackWebmastersRetrieval + notes: Created by mteb + value: 0.31381 diff --git a/.eval_results/CQADupstackWordpressRetrieval.yaml b/.eval_results/CQADupstackWordpressRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..30be5a7d4250b135c6cd866609705cd964fa7eab --- /dev/null +++ b/.eval_results/CQADupstackWordpressRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/cqadupstack-wordpress + revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 + task_id: CQADupstackWordpressRetrieval_default_test + notes: Created by mteb + value: 0.27925 +- dataset: + id: mteb/cqadupstack-wordpress + revision: 4ffe81d471b1924886b33c7567bfb200e9eec5c4 + task_id: CQADupstackWordpressRetrieval + notes: Created by mteb + value: 0.27925 diff --git a/.eval_results/CUREv1.yaml b/.eval_results/CUREv1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d6b4888cb501d84bcbb2fb03553bce0a61b8690f --- /dev/null +++ b/.eval_results/CUREv1.yaml @@ -0,0 +1,204 @@ +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_all + notes: Created by mteb + value: 0.35481 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_all + notes: Created by mteb + value: 0.01157 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_all + notes: Created by mteb + value: 0.01796 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_dentistry_and_oral_health + notes: Created by mteb + value: 0.38853 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_dentistry_and_oral_health + notes: Created by mteb + value: 0.00791 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_dentistry_and_oral_health + notes: Created by mteb + value: 0.0137 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_dermatology + notes: Created by mteb + value: 0.40305 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_dermatology + notes: Created by mteb + value: 0.04687 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_dermatology + notes: Created by mteb + value: 0.07281 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_gastroenterology + notes: Created by mteb + value: 0.30019 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_gastroenterology + notes: Created by mteb + value: 0.01412 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_gastroenterology + notes: Created by mteb + value: 0.02969 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_genetics + notes: Created by mteb + value: 0.41022 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_genetics + notes: Created by mteb + value: 0.03798 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_genetics + notes: Created by mteb + value: 0.08926 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_neuroscience_and_neurology + notes: Created by mteb + value: 0.31575 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_neuroscience_and_neurology + notes: Created by mteb + value: 0.00768 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_neuroscience_and_neurology + notes: Created by mteb + value: 0.02533 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_orthopedic_surgery + notes: Created by mteb + value: 0.39297 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_orthopedic_surgery + notes: Created by mteb + value: 0.02131 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_orthopedic_surgery + notes: Created by mteb + value: 0.04247 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_otorhinolaryngology + notes: Created by mteb + value: 0.33081 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_otorhinolaryngology + notes: Created by mteb + value: 0.00483 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_otorhinolaryngology + notes: Created by mteb + value: 0.02196 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_plastic_surgery + notes: Created by mteb + value: 0.34636 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_plastic_surgery + notes: Created by mteb + value: 0.01692 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_plastic_surgery + notes: Created by mteb + value: 0.02923 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_psychiatry_and_psychology + notes: Created by mteb + value: 0.34984 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_psychiatry_and_psychology + notes: Created by mteb + value: 0.01113 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_psychiatry_and_psychology + notes: Created by mteb + value: 0.02743 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_en_pulmonology + notes: Created by mteb + value: 0.34924 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_es_pulmonology + notes: Created by mteb + value: 0.01324 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1_fr_pulmonology + notes: Created by mteb + value: 0.01515 +- dataset: + id: clinia/CUREv1 + revision: 3bcf51c91e04d04a8a3329dfbe988b964c5cbe83 + task_id: CUREv1 + notes: Created by mteb + value: 0.13697939393939393 diff --git a/.eval_results/ChatDoctorRetrieval.yaml b/.eval_results/ChatDoctorRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..245d79208f5cd4b501487185901fc7343f7375e1 --- /dev/null +++ b/.eval_results/ChatDoctorRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/ChatDoctor_HealthCareMagic + revision: 50c2986fedffa33b38afd5c1752026f8e9e5ed1d + task_id: ChatDoctorRetrieval_default_test + notes: Created by mteb + value: 0.31764 +- dataset: + id: embedding-benchmark/ChatDoctor_HealthCareMagic + revision: 50c2986fedffa33b38afd5c1752026f8e9e5ed1d + task_id: ChatDoctorRetrieval + notes: Created by mteb + value: 0.31764 diff --git a/.eval_results/ClimateFEVER.yaml b/.eval_results/ClimateFEVER.yaml new file mode 100644 index 0000000000000000000000000000000000000000..33043831d15565eba6446b7005966eaab87a8cf8 --- /dev/null +++ b/.eval_results/ClimateFEVER.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/climate-fever + revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 + task_id: ClimateFEVER_default_test + notes: Created by mteb + value: 0.13621 +- dataset: + id: mteb/climate-fever + revision: 47f2ac6acb640fc46020b02a5b59fdda04d39380 + task_id: ClimateFEVER + notes: Created by mteb + value: 0.13621 diff --git a/.eval_results/CmedqaRetrieval.yaml b/.eval_results/CmedqaRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..377454fa3f163996181c367d2e4d585eaf67233b --- /dev/null +++ b/.eval_results/CmedqaRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/CmedqaRetrieval + revision: c476f85bf03d6642ec66bf54b9a551c88108bbb4 + task_id: CmedqaRetrieval_default_dev + notes: Created by mteb + value: 0.01337 +- dataset: + id: mteb/CmedqaRetrieval + revision: c476f85bf03d6642ec66bf54b9a551c88108bbb4 + task_id: CmedqaRetrieval + notes: Created by mteb + value: 0.01337 diff --git a/.eval_results/Code1Retrieval.yaml b/.eval_results/Code1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d0b9eb7a40ee1f3adba0cdc76d16465564ecd339 --- /dev/null +++ b/.eval_results/Code1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/Code1Retrieval + revision: 94d25599a7e0221484f31749448e5ea217484e41 + task_id: Code1Retrieval_default_test + notes: Created by mteb + value: 0.44744 +- dataset: + id: mteb-private/Code1Retrieval + revision: 94d25599a7e0221484f31749448e5ea217484e41 + task_id: Code1Retrieval + notes: Created by mteb + value: 0.44744 diff --git a/.eval_results/DBPedia.yaml b/.eval_results/DBPedia.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8e570f3843abbc7f4160526aa0bc76f45c5d8cb8 --- /dev/null +++ b/.eval_results/DBPedia.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/dbpedia + revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 + task_id: DBPedia_default_dev + notes: Created by mteb + value: 0.34447 +- dataset: + id: mteb/dbpedia + revision: c0f706b76e590d620bd6618b3ca8efdd34e2d659 + task_id: DBPedia_default_test + notes: Created by mteb + value: 0.29907 diff --git a/.eval_results/DS1000Retrieval.yaml b/.eval_results/DS1000Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a40b9cbc3af96ae8fd2d79a01562f5af79201174 --- /dev/null +++ b/.eval_results/DS1000Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/DS1000 + revision: 25cd4dc8172e799235d83c66439b6b7b8e6583ec + task_id: DS1000Retrieval_default_test + notes: Created by mteb + value: 0.41454 +- dataset: + id: embedding-benchmark/DS1000 + revision: 25cd4dc8172e799235d83c66439b6b7b8e6583ec + task_id: DS1000Retrieval + notes: Created by mteb + value: 0.41454 diff --git a/.eval_results/EnglishFinance1Retrieval.yaml b/.eval_results/EnglishFinance1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..62ad9d01e93a187167adc9ca44d11ec7dd078ecc --- /dev/null +++ b/.eval_results/EnglishFinance1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/EnglishFinance1Retrieval + revision: b2816ead5389ee383019bb2e50df9f1aac8229d8 + task_id: EnglishFinance1Retrieval_default_test + notes: Created by mteb + value: 0.75345 +- dataset: + id: mteb-private/EnglishFinance1Retrieval + revision: b2816ead5389ee383019bb2e50df9f1aac8229d8 + task_id: EnglishFinance1Retrieval + notes: Created by mteb + value: 0.75345 diff --git a/.eval_results/EnglishFinance2Retrieval.yaml b/.eval_results/EnglishFinance2Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6afd19abcec070038ee9f41f60fb566ca3e27ffc --- /dev/null +++ b/.eval_results/EnglishFinance2Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/EnglishFinance2Retrieval + revision: 346d5039b9ec75a7b80f8ff008d5ca3df126f5aa + task_id: EnglishFinance2Retrieval_default_test + notes: Created by mteb + value: 0.76472 +- dataset: + id: mteb-private/EnglishFinance2Retrieval + revision: 346d5039b9ec75a7b80f8ff008d5ca3df126f5aa + task_id: EnglishFinance2Retrieval + notes: Created by mteb + value: 0.76472 diff --git a/.eval_results/EnglishFinance3Retrieval.yaml b/.eval_results/EnglishFinance3Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5581c33cdb3b82a428b985e9f34ef377abfcdc3d --- /dev/null +++ b/.eval_results/EnglishFinance3Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/EnglishFinance3Retrieval + revision: 5ed0bc0fffa309e99400ea800397931749d12cd2 + task_id: EnglishFinance3Retrieval_default_test + notes: Created by mteb + value: 0.45123 +- dataset: + id: mteb-private/EnglishFinance3Retrieval + revision: 5ed0bc0fffa309e99400ea800397931749d12cd2 + task_id: EnglishFinance3Retrieval + notes: Created by mteb + value: 0.45123 diff --git a/.eval_results/EnglishFinance4Retrieval.yaml b/.eval_results/EnglishFinance4Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a3443d92d0ca15666b9c0a7c5e34a7ec3a457837 --- /dev/null +++ b/.eval_results/EnglishFinance4Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/EnglishFinance4Retrieval + revision: 2fdb7001309f897d50d38d196a3fd0f03c913810 + task_id: EnglishFinance4Retrieval_default_test + notes: Created by mteb + value: 0.3173 +- dataset: + id: mteb-private/EnglishFinance4Retrieval + revision: 2fdb7001309f897d50d38d196a3fd0f03c913810 + task_id: EnglishFinance4Retrieval + notes: Created by mteb + value: 0.3173 diff --git a/.eval_results/EnglishHealthcare1Retrieval.yaml b/.eval_results/EnglishHealthcare1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9b89967fe121c18e6ed725d2d30ad45efff11b0e --- /dev/null +++ b/.eval_results/EnglishHealthcare1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/EnglishHealthcare1Retrieval + revision: 393c24e85114d44c43259fb2d1c5639c5d09809d + task_id: EnglishHealthcare1Retrieval_default_test + notes: Created by mteb + value: 0.68748 +- dataset: + id: mteb-private/EnglishHealthcare1Retrieval + revision: 393c24e85114d44c43259fb2d1c5639c5d09809d + task_id: EnglishHealthcare1Retrieval + notes: Created by mteb + value: 0.68748 diff --git a/.eval_results/FEVER.yaml b/.eval_results/FEVER.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e25a1a3ea7ca95eb6eb4bb3ac88b5428999584a0 --- /dev/null +++ b/.eval_results/FEVER.yaml @@ -0,0 +1,18 @@ +- dataset: + id: mteb/fever + revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 + task_id: FEVER_default_dev + notes: Created by mteb + value: 0.49778 +- dataset: + id: mteb/fever + revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 + task_id: FEVER_default_test + notes: Created by mteb + value: 0.4809 +- dataset: + id: mteb/fever + revision: bea83ef9e8fb933d90a2f1d5515737465d613e12 + task_id: FEVER_default_train + notes: Created by mteb + value: 0.38431 diff --git a/.eval_results/FiQA2018.yaml b/.eval_results/FiQA2018.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fd08127034cffb79a00ce270ba1ec56e4c631ec6 --- /dev/null +++ b/.eval_results/FiQA2018.yaml @@ -0,0 +1,18 @@ +- dataset: + id: mteb/fiqa + revision: 27a168819829fe9bcd655c2df245fb19452e8e06 + task_id: FiQA2018_default_dev + notes: Created by mteb + value: 0.2592 +- dataset: + id: mteb/fiqa + revision: 27a168819829fe9bcd655c2df245fb19452e8e06 + task_id: FiQA2018_default_test + notes: Created by mteb + value: 0.25139 +- dataset: + id: mteb/fiqa + revision: 27a168819829fe9bcd655c2df245fb19452e8e06 + task_id: FiQA2018_default_train + notes: Created by mteb + value: 0.24794 diff --git a/.eval_results/FinQARetrieval.yaml b/.eval_results/FinQARetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d476fb3600fd8cc1b49cd0908c253b953b6ad7a9 --- /dev/null +++ b/.eval_results/FinQARetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/FinQA + revision: bdd1903ce03153129480bfc14b710e3d612c1efd + task_id: FinQARetrieval_default_test + notes: Created by mteb + value: 0.73872 +- dataset: + id: embedding-benchmark/FinQA + revision: bdd1903ce03153129480bfc14b710e3d612c1efd + task_id: FinQARetrieval + notes: Created by mteb + value: 0.73872 diff --git a/.eval_results/FinanceBenchRetrieval.yaml b/.eval_results/FinanceBenchRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8214cf536dfd5b5088c6e184b3204479905ae5e6 --- /dev/null +++ b/.eval_results/FinanceBenchRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/FinanceBench + revision: e68478442112cae36b70a216f52cc2777acf0a7e + task_id: FinanceBenchRetrieval_default_test + notes: Created by mteb + value: 0.46676 +- dataset: + id: embedding-benchmark/FinanceBench + revision: e68478442112cae36b70a216f52cc2777acf0a7e + task_id: FinanceBenchRetrieval + notes: Created by mteb + value: 0.46676 diff --git a/.eval_results/French1Retrieval.yaml b/.eval_results/French1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c3b71b9336c268211435bc60380b4c4cd82d8fa7 --- /dev/null +++ b/.eval_results/French1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/French1Retrieval + revision: c5c5a44f75dff57be44e5623e817239b050bf0f2 + task_id: French1Retrieval_default_test + notes: Created by mteb + value: 0.78323 +- dataset: + id: mteb-private/French1Retrieval + revision: c5c5a44f75dff57be44e5623e817239b050bf0f2 + task_id: French1Retrieval + notes: Created by mteb + value: 0.78323 diff --git a/.eval_results/FrenchLegal1Retrieval.yaml b/.eval_results/FrenchLegal1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a62a300ba1790ff681bfcdbf311fe976fd9774e4 --- /dev/null +++ b/.eval_results/FrenchLegal1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/FrenchLegal1Retrieval + revision: 6d7308571a1572e22d5c0c1cb87385a7bb6b2c6d + task_id: FrenchLegal1Retrieval_default_test + notes: Created by mteb + value: 0.94897 +- dataset: + id: mteb-private/FrenchLegal1Retrieval + revision: 6d7308571a1572e22d5c0c1cb87385a7bb6b2c6d + task_id: FrenchLegal1Retrieval + notes: Created by mteb + value: 0.94897 diff --git a/.eval_results/FreshStackRetrieval.yaml b/.eval_results/FreshStackRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4f0c5ee4025194d4ae6eb23b071885b4c696e0e5 --- /dev/null +++ b/.eval_results/FreshStackRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/FreshStack_mteb + revision: 7a20df1abe4dafc46f93f9a7965bf9c6968bdf04 + task_id: FreshStackRetrieval_default_test + notes: Created by mteb + value: 0.27888 +- dataset: + id: embedding-benchmark/FreshStack_mteb + revision: 7a20df1abe4dafc46f93f9a7965bf9c6968bdf04 + task_id: FreshStackRetrieval + notes: Created by mteb + value: 0.27888 diff --git a/.eval_results/German1Retrieval.yaml b/.eval_results/German1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b210581468b9c375e61283f4207dabef35ebe4ed --- /dev/null +++ b/.eval_results/German1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/German1Retrieval + revision: d83dd140fc8fdf96372a6e9193cd4fd2d5cb72bd + task_id: German1Retrieval_default_test + notes: Created by mteb + value: 0.86465 +- dataset: + id: mteb-private/German1Retrieval + revision: d83dd140fc8fdf96372a6e9193cd4fd2d5cb72bd + task_id: German1Retrieval + notes: Created by mteb + value: 0.86465 diff --git a/.eval_results/GermanHealthcare1Retrieval.yaml b/.eval_results/GermanHealthcare1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..34de46c8c979ccf100ae9b7baa3288ddd91fa3fa --- /dev/null +++ b/.eval_results/GermanHealthcare1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/GermanHealthcare1Retrieval + revision: 53e9a6fb88b48b7513e9d2cc2218e3415f4e45f8 + task_id: GermanHealthcare1Retrieval_default_test + notes: Created by mteb + value: 0.37248 +- dataset: + id: mteb-private/GermanHealthcare1Retrieval + revision: 53e9a6fb88b48b7513e9d2cc2218e3415f4e45f8 + task_id: GermanHealthcare1Retrieval + notes: Created by mteb + value: 0.37248 diff --git a/.eval_results/GermanLegal1Retrieval.yaml b/.eval_results/GermanLegal1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..26c04ae7898374fb371daae75546fd77af868fd0 --- /dev/null +++ b/.eval_results/GermanLegal1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/GermanLegal1Retrieval + revision: 65ea369daff680b77f90b560e7e97d2ab4ec5072 + task_id: GermanLegal1Retrieval_default_test + notes: Created by mteb + value: 0.66876 +- dataset: + id: mteb-private/GermanLegal1Retrieval + revision: 65ea369daff680b77f90b560e7e97d2ab4ec5072 + task_id: GermanLegal1Retrieval + notes: Created by mteb + value: 0.66876 diff --git a/.eval_results/HC3FinanceRetrieval.yaml b/.eval_results/HC3FinanceRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6d7b204873a89a7f793fb3e5f525e62581fc85eb --- /dev/null +++ b/.eval_results/HC3FinanceRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/HC3Finance + revision: fda6fad068f2ed814d99f29dc95dbb28ac586943 + task_id: HC3FinanceRetrieval_default_test + notes: Created by mteb + value: 0.28977 +- dataset: + id: embedding-benchmark/HC3Finance + revision: fda6fad068f2ed814d99f29dc95dbb28ac586943 + task_id: HC3FinanceRetrieval + notes: Created by mteb + value: 0.28977 diff --git a/.eval_results/HotpotQA.yaml b/.eval_results/HotpotQA.yaml new file mode 100644 index 0000000000000000000000000000000000000000..270c4d600619e362df1d7535b062b12656631530 --- /dev/null +++ b/.eval_results/HotpotQA.yaml @@ -0,0 +1,18 @@ +- dataset: + id: mteb/hotpotqa + revision: ab518f4d6fcca38d87c25209f94beba119d02014 + task_id: HotpotQA_default_dev + notes: Created by mteb + value: 0.59451 +- dataset: + id: mteb/hotpotqa + revision: ab518f4d6fcca38d87c25209f94beba119d02014 + task_id: HotpotQA_default_test + notes: Created by mteb + value: 0.56907 +- dataset: + id: mteb/hotpotqa + revision: ab518f4d6fcca38d87c25209f94beba119d02014 + task_id: HotpotQA_default_train + notes: Created by mteb + value: 0.58909 diff --git a/.eval_results/HumanEvalRetrieval.yaml b/.eval_results/HumanEvalRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2632f631d32c26e5e983e7ac66d5de6addf095a0 --- /dev/null +++ b/.eval_results/HumanEvalRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/HumanEval + revision: ed1f48aca747f10bac146795328e2f03326e7625 + task_id: HumanEvalRetrieval_default_test + notes: Created by mteb + value: 0.38472 +- dataset: + id: embedding-benchmark/HumanEval + revision: ed1f48aca747f10bac146795328e2f03326e7625 + task_id: HumanEvalRetrieval + notes: Created by mteb + value: 0.38472 diff --git a/.eval_results/JaCWIRRetrieval.yaml b/.eval_results/JaCWIRRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0c002647bcd689cc4caa00e76b8752b388f1ac29 --- /dev/null +++ b/.eval_results/JaCWIRRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/JaCWIRRetrieval + revision: abf6d5fb6759ad516f998bd887b75420d595672e + task_id: JaCWIRRetrieval_default_test + notes: Created by mteb + value: 0.19066 +- dataset: + id: mteb/JaCWIRRetrieval + revision: abf6d5fb6759ad516f998bd887b75420d595672e + task_id: JaCWIRRetrieval + notes: Created by mteb + value: 0.19066 diff --git a/.eval_results/JaGovFaqsRetrieval.yaml b/.eval_results/JaGovFaqsRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8bf614830948b07a77de85828a76f583f1eb9ebb --- /dev/null +++ b/.eval_results/JaGovFaqsRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/JaGovFaqsRetrieval + revision: 0726b2af53c907628067871e2e7c84e0d8e099c2 + task_id: JaGovFaqsRetrieval_default_test + notes: Created by mteb + value: 0.12557 +- dataset: + id: mteb/JaGovFaqsRetrieval + revision: 0726b2af53c907628067871e2e7c84e0d8e099c2 + task_id: JaGovFaqsRetrieval + notes: Created by mteb + value: 0.12557 diff --git a/.eval_results/JapaneseCode1Retrieval.yaml b/.eval_results/JapaneseCode1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7132c1d58407e0b1de59506f236e43a4e8169f61 --- /dev/null +++ b/.eval_results/JapaneseCode1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/JapaneseCode1Retrieval + revision: fc4cb6390055e65490dfc42526e1d6a379e8cd86 + task_id: JapaneseCode1Retrieval_default_test + notes: Created by mteb + value: 0.33855 +- dataset: + id: mteb-private/JapaneseCode1Retrieval + revision: fc4cb6390055e65490dfc42526e1d6a379e8cd86 + task_id: JapaneseCode1Retrieval + notes: Created by mteb + value: 0.33855 diff --git a/.eval_results/JapaneseLegal1Retrieval.yaml b/.eval_results/JapaneseLegal1Retrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..823dccc042eff40467be7d34390ec6c36b132708 --- /dev/null +++ b/.eval_results/JapaneseLegal1Retrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb-private/JapaneseLegal1Retrieval + revision: d653557fe66bb6af2b0e2adfc371a24554cf11ce + task_id: JapaneseLegal1Retrieval_default_test + notes: Created by mteb + value: 0.11133 +- dataset: + id: mteb-private/JapaneseLegal1Retrieval + revision: d653557fe66bb6af2b0e2adfc371a24554cf11ce + task_id: JapaneseLegal1Retrieval + notes: Created by mteb + value: 0.11133 diff --git a/.eval_results/JaqketRetrieval.yaml b/.eval_results/JaqketRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5c50a997b41fd1a6dcbb31331f53da93f5fcc266 --- /dev/null +++ b/.eval_results/JaqketRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/jaqket + revision: 3a5b92dad489a61e664c05ed2175bc9220230199 + task_id: JaqketRetrieval_default_test + notes: Created by mteb + value: 0.13284 +- dataset: + id: mteb/jaqket + revision: 3a5b92dad489a61e664c05ed2175bc9220230199 + task_id: JaqketRetrieval + notes: Created by mteb + value: 0.13284 diff --git a/.eval_results/LegalQuAD.yaml b/.eval_results/LegalQuAD.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8aba169fcf6eab44e4d403ef7c92d4a12c7e3be3 --- /dev/null +++ b/.eval_results/LegalQuAD.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/LegalQuAD + revision: 37aa6cfb01d48960b0f8e3f17d6e3d99bf1ebc3e + task_id: LegalQuAD_default_test + notes: Created by mteb + value: 0.76755 +- dataset: + id: mteb/LegalQuAD + revision: 37aa6cfb01d48960b0f8e3f17d6e3d99bf1ebc3e + task_id: LegalQuAD + notes: Created by mteb + value: 0.76755 diff --git a/.eval_results/LegalSummarization.yaml b/.eval_results/LegalSummarization.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8e861a6d5d90acf7a2df6bcd81c8cb5f403707af --- /dev/null +++ b/.eval_results/LegalSummarization.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/legal_summarization + revision: 3bb1a05c66872889662af04c5691c14489cebd72 + task_id: LegalSummarization_default_test + notes: Created by mteb + value: 0.60983 +- dataset: + id: mteb/legal_summarization + revision: 3bb1a05c66872889662af04c5691c14489cebd72 + task_id: LegalSummarization + notes: Created by mteb + value: 0.60983 diff --git a/.eval_results/MBPPRetrieval.yaml b/.eval_results/MBPPRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3659c664391e9b56975df9f59aa83eb5b990a53b --- /dev/null +++ b/.eval_results/MBPPRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/MBPP + revision: 586a1fd6a0c63fdeda3b49c0293559a81c79cdec + task_id: MBPPRetrieval_default_test + notes: Created by mteb + value: 0.11637 +- dataset: + id: embedding-benchmark/MBPP + revision: 586a1fd6a0c63fdeda3b49c0293559a81c79cdec + task_id: MBPPRetrieval + notes: Created by mteb + value: 0.11637 diff --git a/.eval_results/MIRACLRetrieval.yaml b/.eval_results/MIRACLRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e379641e0ab6a69e6eac62ae067f3d9f1db405d9 --- /dev/null +++ b/.eval_results/MIRACLRetrieval.yaml @@ -0,0 +1,6 @@ +- dataset: + id: mteb/MIRACLRetrieval + revision: 9c09abc13478308c27598f350e31d8f06b9b5481 + task_id: MIRACLRetrieval_ja_dev + notes: Created by mteb + value: 0.04483 diff --git a/.eval_results/MIRACLRetrievalHardNegatives.yaml b/.eval_results/MIRACLRetrievalHardNegatives.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b220ab4e3d6f1d822ac032354b21b6a0f87d1080 --- /dev/null +++ b/.eval_results/MIRACLRetrievalHardNegatives.yaml @@ -0,0 +1,114 @@ +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_ar_dev + notes: Created by mteb + value: 0.38751 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_bn_dev + notes: Created by mteb + value: 0.2095 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_de_dev + notes: Created by mteb + value: 0.14575 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_en_dev + notes: Created by mteb + value: 0.27901 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_es_dev + notes: Created by mteb + value: 0.24337 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_fa_dev + notes: Created by mteb + value: 0.29789 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_fi_dev + notes: Created by mteb + value: 0.41906 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_fr_dev + notes: Created by mteb + value: 0.1563 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_hi_dev + notes: Created by mteb + value: 0.1668 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_id_dev + notes: Created by mteb + value: 0.33772 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_ja_dev + notes: Created by mteb + value: 0.05488 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_ko_dev + notes: Created by mteb + value: 0.28846 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_ru_dev + notes: Created by mteb + value: 0.19821 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_sw_dev + notes: Created by mteb + value: 0.40954 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_te_dev + notes: Created by mteb + value: 0.12991 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_th_dev + notes: Created by mteb + value: 0.34631 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_yo_dev + notes: Created by mteb + value: 0.50239 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives_zh_dev + notes: Created by mteb + value: 0.00101 +- dataset: + id: mteb/MIRACLRetrievalHardNegatives + revision: d7d94fa4b946cec4a27c84653aa0cf6b33f74a3c + task_id: MIRACLRetrievalHardNegatives + notes: Created by mteb + value: 0.25409 diff --git a/.eval_results/MSMARCO.yaml b/.eval_results/MSMARCO.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7744b1a0e19c23d0dc3348ba7c05e91e83f4b13d --- /dev/null +++ b/.eval_results/MSMARCO.yaml @@ -0,0 +1,18 @@ +- dataset: + id: mteb/msmarco + revision: c5a29a104738b98a9e76336939199e264163d4a0 + task_id: MSMARCO_default_dev + notes: Created by mteb + value: 0.21888 +- dataset: + id: mteb/msmarco + revision: c5a29a104738b98a9e76336939199e264163d4a0 + task_id: MSMARCO_default_test + notes: Created by mteb + value: 0.46311 +- dataset: + id: mteb/msmarco + revision: c5a29a104738b98a9e76336939199e264163d4a0 + task_id: MSMARCO_default_train + notes: Created by mteb + value: 0.19915 diff --git a/.eval_results/MedicalQARetrieval.yaml b/.eval_results/MedicalQARetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4c16dd5f61bb6bb80afbb944911df9865fe02096 --- /dev/null +++ b/.eval_results/MedicalQARetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/medical_qa + revision: ae763399273d8b20506b80cf6f6f9a31a6a2b238 + task_id: MedicalQARetrieval_default_test + notes: Created by mteb + value: 0.45831 +- dataset: + id: mteb/medical_qa + revision: ae763399273d8b20506b80cf6f6f9a31a6a2b238 + task_id: MedicalQARetrieval + notes: Created by mteb + value: 0.45831 diff --git a/.eval_results/MintakaRetrieval.yaml b/.eval_results/MintakaRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7227fef96f941c903b28bf86180461fd2a6d3596 --- /dev/null +++ b/.eval_results/MintakaRetrieval.yaml @@ -0,0 +1,6 @@ +- dataset: + id: mteb/MintakaRetrieval + revision: 43bc699486e768138ce3a6d4cd859da306ac9eef + task_id: MintakaRetrieval_ja_test + notes: Created by mteb + value: 0.03786 diff --git a/.eval_results/MrTidyRetrieval.yaml b/.eval_results/MrTidyRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bc381fd77f9c2bba7da06d0d71b2f4c68bb4e3c8 --- /dev/null +++ b/.eval_results/MrTidyRetrieval.yaml @@ -0,0 +1,6 @@ +- dataset: + id: mteb/mrtidy + revision: fc24a3ce8f09746410daee3d5cd823ff7a0675b7 + task_id: MrTidyRetrieval_japanese_test + notes: Created by mteb + value: 0.02256 diff --git a/.eval_results/MultiLongDocRetrieval.yaml b/.eval_results/MultiLongDocRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c52bda10164096ff1c4bd202e64bbc72142e3262 --- /dev/null +++ b/.eval_results/MultiLongDocRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/MultiLongDocRetrieval + revision: 837028901907a7d419b4ab906f28e011ce1cc824 + task_id: MultiLongDocRetrieval_ja_dev + notes: Created by mteb + value: 0.1334 +- dataset: + id: mteb/MultiLongDocRetrieval + revision: 837028901907a7d419b4ab906f28e011ce1cc824 + task_id: MultiLongDocRetrieval_ja_test + notes: Created by mteb + value: 0.11252 diff --git a/.eval_results/NFCorpus.yaml b/.eval_results/NFCorpus.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fe50e9dddc8c3f450d621372be8917e21ea07179 --- /dev/null +++ b/.eval_results/NFCorpus.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/nfcorpus + revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 + task_id: NFCorpus_default_test + notes: Created by mteb + value: 0.32082 +- dataset: + id: mteb/nfcorpus + revision: ec0fa4fe99da2ff19ca1214b7966684033a58814 + task_id: NFCorpus + notes: Created by mteb + value: 0.32082 diff --git a/.eval_results/NLPJournalAbsArticleRetrieval.V2.yaml b/.eval_results/NLPJournalAbsArticleRetrieval.V2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..893b27400d1a5d171848e78cb85be521de67db73 --- /dev/null +++ b/.eval_results/NLPJournalAbsArticleRetrieval.V2.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/NLPJournalAbsArticleRetrieval.V2 + revision: 683ad149644acc21180dceeac3a5c57eac171df3 + task_id: NLPJournalAbsArticleRetrieval.V2_default_test + notes: Created by mteb + value: 0.8307 +- dataset: + id: mteb/NLPJournalAbsArticleRetrieval.V2 + revision: 683ad149644acc21180dceeac3a5c57eac171df3 + task_id: NLPJournalAbsArticleRetrieval.V2 + notes: Created by mteb + value: 0.8307 diff --git a/.eval_results/NLPJournalAbsIntroRetrieval.V2.yaml b/.eval_results/NLPJournalAbsIntroRetrieval.V2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5ab38c564de67f7b487e40c6769cf58f3243fef9 --- /dev/null +++ b/.eval_results/NLPJournalAbsIntroRetrieval.V2.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/NLPJournalAbsIntroRetrieval.V2 + revision: 8a7ae2cbcd62a3df5a880f4e4afff30a977afe0d + task_id: NLPJournalAbsIntroRetrieval.V2_default_test + notes: Created by mteb + value: 0.69512 +- dataset: + id: mteb/NLPJournalAbsIntroRetrieval.V2 + revision: 8a7ae2cbcd62a3df5a880f4e4afff30a977afe0d + task_id: NLPJournalAbsIntroRetrieval.V2 + notes: Created by mteb + value: 0.69512 diff --git a/.eval_results/NLPJournalTitleAbsRetrieval.V2.yaml b/.eval_results/NLPJournalTitleAbsRetrieval.V2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a044df2f62a93081f540817db88d0ecba0cb8124 --- /dev/null +++ b/.eval_results/NLPJournalTitleAbsRetrieval.V2.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/NLPJournalTitleAbsRetrieval.V2 + revision: 7ea085c4107e8554f92409193358790fe40516f8 + task_id: NLPJournalTitleAbsRetrieval.V2_default_test + notes: Created by mteb + value: 0.0793 +- dataset: + id: mteb/NLPJournalTitleAbsRetrieval.V2 + revision: 7ea085c4107e8554f92409193358790fe40516f8 + task_id: NLPJournalTitleAbsRetrieval.V2 + notes: Created by mteb + value: 0.0793 diff --git a/.eval_results/NLPJournalTitleIntroRetrieval.V2.yaml b/.eval_results/NLPJournalTitleIntroRetrieval.V2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..38a9106accf7b128acdebd919b71fb66268772de --- /dev/null +++ b/.eval_results/NLPJournalTitleIntroRetrieval.V2.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/NLPJournalTitleIntroRetrieval.V2 + revision: 39b53c8298ce1948d2a4caaa55fee5b34eeb647e + task_id: NLPJournalTitleIntroRetrieval.V2_default_test + notes: Created by mteb + value: 0.08549 +- dataset: + id: mteb/NLPJournalTitleIntroRetrieval.V2 + revision: 39b53c8298ce1948d2a4caaa55fee5b34eeb647e + task_id: NLPJournalTitleIntroRetrieval.V2 + notes: Created by mteb + value: 0.08549 diff --git a/.eval_results/NQ.yaml b/.eval_results/NQ.yaml new file mode 100644 index 0000000000000000000000000000000000000000..357dd6b437b9d672dc32d7f55840906530938af2 --- /dev/null +++ b/.eval_results/NQ.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/nq + revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 + task_id: NQ_default_test + notes: Created by mteb + value: 0.285 +- dataset: + id: mteb/nq + revision: b774495ed302d8c44a3a7ea25c90dbce03968f31 + task_id: NQ + notes: Created by mteb + value: 0.285 diff --git a/.eval_results/QuoraRetrieval.yaml b/.eval_results/QuoraRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c0daf283385c6e2dcc77252d912390fb73679840 --- /dev/null +++ b/.eval_results/QuoraRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/quora + revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 + task_id: QuoraRetrieval_default_dev + notes: Created by mteb + value: 0.80243 +- dataset: + id: mteb/quora + revision: e4e08e0b7dbe3c8700f0daef558ff32256715259 + task_id: QuoraRetrieval_default_test + notes: Created by mteb + value: 0.80424 diff --git a/.eval_results/SCIDOCS.yaml b/.eval_results/SCIDOCS.yaml new file mode 100644 index 0000000000000000000000000000000000000000..582fecca20d30298d4faf06843a6f74d17675d1d --- /dev/null +++ b/.eval_results/SCIDOCS.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/scidocs + revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 + task_id: SCIDOCS_default_test + notes: Created by mteb + value: 0.15783 +- dataset: + id: mteb/scidocs + revision: f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88 + task_id: SCIDOCS + notes: Created by mteb + value: 0.15783 diff --git a/.eval_results/SciFact-PL.yaml b/.eval_results/SciFact-PL.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c6a2dc8bdc6bf33997b9a3a748ecbdcde2446d44 --- /dev/null +++ b/.eval_results/SciFact-PL.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/SciFact-PL + revision: d9707265734052a21d5892b6300ca11028fa067b + task_id: SciFact-PL_default_test + notes: Created by mteb + value: 0.56361 +- dataset: + id: mteb/SciFact-PL + revision: d9707265734052a21d5892b6300ca11028fa067b + task_id: SciFact-PL + notes: Created by mteb + value: 0.56361 diff --git a/.eval_results/SciFact.yaml b/.eval_results/SciFact.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5ccae9fa6aa9e244a2c0e8507ab305ecd350e01c --- /dev/null +++ b/.eval_results/SciFact.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/scifact + revision: d56462d0e63a25450459c4f213e49ffdb866f7f9 + task_id: SciFact_default_test + notes: Created by mteb + value: 0.68736 +- dataset: + id: mteb/scifact + revision: d56462d0e63a25450459c4f213e49ffdb866f7f9 + task_id: SciFact_default_train + notes: Created by mteb + value: 0.696 diff --git a/.eval_results/TRECCOVID-PL.yaml b/.eval_results/TRECCOVID-PL.yaml new file mode 100644 index 0000000000000000000000000000000000000000..666e51c535e5eae487fb59e566826dab5af7aea4 --- /dev/null +++ b/.eval_results/TRECCOVID-PL.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/TRECCOVID-PL + revision: 1e710582482d4199ff690e5dd2491a70627523f5 + task_id: TRECCOVID-PL_default_test + notes: Created by mteb + value: 0.44601 +- dataset: + id: mteb/TRECCOVID-PL + revision: 1e710582482d4199ff690e5dd2491a70627523f5 + task_id: TRECCOVID-PL + notes: Created by mteb + value: 0.44601 diff --git a/.eval_results/TRECCOVID.yaml b/.eval_results/TRECCOVID.yaml new file mode 100644 index 0000000000000000000000000000000000000000..93d3ed14f21c62db7e357bdccf58f54ba6d7950e --- /dev/null +++ b/.eval_results/TRECCOVID.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/trec-covid + revision: bb9466bac8153a0349341eb1b22e06409e78ef4e + task_id: TRECCOVID_default_test + notes: Created by mteb + value: 0.62314 +- dataset: + id: mteb/trec-covid + revision: bb9466bac8153a0349341eb1b22e06409e78ef4e + task_id: TRECCOVID + notes: Created by mteb + value: 0.62314 diff --git a/.eval_results/Touche2020.yaml b/.eval_results/Touche2020.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8cfe2a3b30f7bebb312eabf822b3f8383995e2b6 --- /dev/null +++ b/.eval_results/Touche2020.yaml @@ -0,0 +1,12 @@ +- dataset: + id: mteb/touche2020 + revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f + task_id: Touche2020_default_test + notes: Created by mteb + value: 0.33053 +- dataset: + id: mteb/touche2020 + revision: a34f9a33db75fa0cbb21bb5cfc3dae8dc8bec93f + task_id: Touche2020 + notes: Created by mteb + value: 0.33053 diff --git a/.eval_results/WikiSQLRetrieval.yaml b/.eval_results/WikiSQLRetrieval.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0db74b9f344ca4d17d203c76f49582e374e839d7 --- /dev/null +++ b/.eval_results/WikiSQLRetrieval.yaml @@ -0,0 +1,12 @@ +- dataset: + id: embedding-benchmark/WikiSQL_mteb + revision: 4e099ab42dffd49d72c1472f451371e53343e3d7 + task_id: WikiSQLRetrieval_default_test + notes: Created by mteb + value: 0.52156 +- dataset: + id: embedding-benchmark/WikiSQL_mteb + revision: 4e099ab42dffd49d72c1472f451371e53343e3d7 + task_id: WikiSQLRetrieval + notes: Created by mteb + value: 0.52156