From 9ebd921bcb99796cb196bd2ef73e680de7ebfd5b Mon Sep 17 00:00:00 2001 From: Ken Wang Date: Thu, 14 Nov 2024 02:07:46 -0800 Subject: [PATCH] add results for keeeeenw/MicroLlama-text-embedding (#46) --- .../AmazonCounterfactualClassification.json | 179 ++++++++++++++++++ .../AmazonPolarityClassification.json | 95 ++++++++++ .../AmazonReviewsClassification.json | 73 +++++++ .../ArXivHierarchicalClusteringP2P.json | 46 +++++ .../ArXivHierarchicalClusteringS2S.json | 46 +++++ .../ArguAna.json | 158 ++++++++++++++++ .../ArxivClusteringP2P.json | 53 ++++++ .../AskUbuntuDupQuestions.json | 26 +++ .../BIOSSES.json | 26 +++ .../Banking77Classification.json | 73 +++++++ .../BiorxivClusteringP2P.v2.json | 34 ++++ .../CQADupstackGamingRetrieval.json | 158 ++++++++++++++++ .../CQADupstackUnixRetrieval.json | 158 ++++++++++++++++ .../ClimateFEVERHardNegatives.json | 158 ++++++++++++++++ .../FEVERHardNegatives.json | 158 ++++++++++++++++ .../FiQA2018.json | 158 ++++++++++++++++ .../HotpotQAHardNegatives.json | 158 ++++++++++++++++ .../ImdbClassification.json | 95 ++++++++++ .../MTOPDomainClassification.json | 73 +++++++ .../MassiveIntentClassification.json | 73 +++++++ .../MassiveScenarioClassification.json | 73 +++++++ .../MedrxivClusteringP2P.v2.json | 34 ++++ .../MedrxivClusteringS2S.v2.json | 34 ++++ .../model_meta.json | 1 + 24 files changed, 2140 insertions(+) create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonCounterfactualClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonPolarityClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonReviewsClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringP2P.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringS2S.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArguAna.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArxivClusteringP2P.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AskUbuntuDupQuestions.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BIOSSES.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/Banking77Classification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BiorxivClusteringP2P.v2.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackGamingRetrieval.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackUnixRetrieval.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ClimateFEVERHardNegatives.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FEVERHardNegatives.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FiQA2018.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/HotpotQAHardNegatives.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ImdbClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MTOPDomainClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveIntentClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveScenarioClassification.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringP2P.v2.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringS2S.v2.json create mode 100644 results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/model_meta.json diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonCounterfactualClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonCounterfactualClassification.json new file mode 100644 index 000000000..f7d72652c --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonCounterfactualClassification.json @@ -0,0 +1,179 @@ +{ + "dataset_revision": "e8379541af4e31359cca9fbcf4b00f2671dba205", + "evaluation_time": 11.987384557723999, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.7337331334332833, + "ap": 0.21853937939763662, + "ap_weighted": 0.21853937939763662, + "f1": 0.6047021327420932, + "f1_weighted": 0.7829868030563938, + "hf_subset": "en-ext", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7337331334332833, + "scores_per_experiment": [ + { + "accuracy": 0.802848575712144, + "ap": 0.253603822178596, + "ap_weighted": 0.253603822178596, + "f1": 0.6575129710707296, + "f1_weighted": 0.834123326078018 + }, + { + "accuracy": 0.6866566716641679, + "ap": 0.20668512763849248, + "ap_weighted": 0.20668512763849248, + "f1": 0.5748936494625295, + "f1_weighted": 0.7474400697036555 + }, + { + "accuracy": 0.732383808095952, + "ap": 0.2165878487007201, + "ap_weighted": 0.2165878487007201, + "f1": 0.6032788114308563, + "f1_weighted": 0.7824310801277565 + }, + { + "accuracy": 0.7338830584707646, + "ap": 0.2313181006683483, + "ap_weighted": 0.2313181006683483, + "f1": 0.6113675623997276, + "f1_weighted": 0.7840996903717105 + }, + { + "accuracy": 0.704647676161919, + "ap": 0.21231496276527717, + "ap_weighted": 0.21231496276527717, + "f1": 0.5869943077701609, + "f1_weighted": 0.7614914384186111 + }, + { + "accuracy": 0.7158920539730135, + "ap": 0.20174624917756948, + "ap_weighted": 0.20174624917756948, + "f1": 0.5871186601237535, + "f1_weighted": 0.7696484640228388 + }, + { + "accuracy": 0.6911544227886057, + "ap": 0.20893594445031208, + "ap_weighted": 0.20893594445031208, + "f1": 0.5783455674760023, + "f1_weighted": 0.7509921634326823 + }, + { + "accuracy": 0.767616191904048, + "ap": 0.21283962335379072, + "ap_weighted": 0.21283962335379072, + "f1": 0.6185055350553506, + "f1_weighted": 0.8073075178278019 + }, + { + "accuracy": 0.7563718140929535, + "ap": 0.23614888342057133, + "ap_weighted": 0.23614888342057133, + "f1": 0.6252922340292213, + "f1_weighted": 0.8007295427076767 + }, + { + "accuracy": 0.7458770614692654, + "ap": 0.20521323162268876, + "ap_weighted": 0.20521323162268876, + "f1": 0.6037120286026, + "f1_weighted": 0.7916047378731865 + } + ] + }, + { + "accuracy": 0.7423880597014926, + "ap": 0.37447869256341476, + "ap_weighted": 0.37447869256341476, + "f1": 0.6838136251649617, + "f1_weighted": 0.7661970582344355, + "hf_subset": "en", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7423880597014926, + "scores_per_experiment": [ + { + "accuracy": 0.6805970149253732, + "ap": 0.3160067410365431, + "ap_weighted": 0.3160067410365431, + "f1": 0.6259951377802819, + "f1_weighted": 0.713016879480271 + }, + { + "accuracy": 0.7970149253731343, + "ap": 0.4395383163598705, + "ap_weighted": 0.4395383163598705, + "f1": 0.7389440872783947, + "f1_weighted": 0.8139216250716027 + }, + { + "accuracy": 0.6895522388059702, + "ap": 0.3361540452298984, + "ap_weighted": 0.3361540452298984, + "f1": 0.6402647420210843, + "f1_weighted": 0.7213506238284771 + }, + { + "accuracy": 0.7253731343283583, + "ap": 0.3523102253901136, + "ap_weighted": 0.3523102253901136, + "f1": 0.6662479424759595, + "f1_weighted": 0.7517907732411321 + }, + { + "accuracy": 0.7895522388059701, + "ap": 0.40282679552395184, + "ap_weighted": 0.40282679552395184, + "f1": 0.7194029850746269, + "f1_weighted": 0.8048384940966806 + }, + { + "accuracy": 0.7417910447761195, + "ap": 0.36612848992794356, + "ap_weighted": 0.36612848992794356, + "f1": 0.6807335608495777, + "f1_weighted": 0.7657555862489942 + }, + { + "accuracy": 0.7865671641791044, + "ap": 0.41328064488817207, + "ap_weighted": 0.41328064488817207, + "f1": 0.7229795957312084, + "f1_weighted": 0.8038011780575062 + }, + { + "accuracy": 0.7820895522388059, + "ap": 0.3990137475187229, + "ap_weighted": 0.3990137475187229, + "f1": 0.7144975249836556, + "f1_weighted": 0.7990912278060524 + }, + { + "accuracy": 0.7059701492537314, + "ap": 0.35855036478570557, + "ap_weighted": 0.35855036478570557, + "f1": 0.6588515348967043, + "f1_weighted": 0.7360579391443631 + }, + { + "accuracy": 0.7253731343283583, + "ap": 0.3609775549732255, + "ap_weighted": 0.3609775549732255, + "f1": 0.6702191405581236, + "f1_weighted": 0.7523462553692759 + } + ] + } + ] + }, + "task_name": "AmazonCounterfactualClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonPolarityClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonPolarityClassification.json new file mode 100644 index 000000000..cd680db83 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonPolarityClassification.json @@ -0,0 +1,95 @@ +{ + "dataset_revision": "e2d317d38cd51312af73b3d32a06d1a08b442046", + "evaluation_time": 1085.8549246788025, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.66766525, + "ap": 0.6179460240681391, + "ap_weighted": 0.6179460240681391, + "f1": 0.664339976948822, + "f1_weighted": 0.664339976948822, + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.66766525, + "scores_per_experiment": [ + { + "accuracy": 0.7112825, + "ap": 0.6579411226560989, + "ap_weighted": 0.6579411226560989, + "f1": 0.709725973236081, + "f1_weighted": 0.709725973236081 + }, + { + "accuracy": 0.634495, + "ap": 0.5858987399082332, + "ap_weighted": 0.5858987399082332, + "f1": 0.6344119180519443, + "f1_weighted": 0.6344119180519444 + }, + { + "accuracy": 0.64797, + "ap": 0.5934658581495289, + "ap_weighted": 0.5934658581495289, + "f1": 0.6466131140766969, + "f1_weighted": 0.6466131140766967 + }, + { + "accuracy": 0.691885, + "ap": 0.6494519509882285, + "ap_weighted": 0.6494519509882285, + "f1": 0.6842047319740125, + "f1_weighted": 0.6842047319740125 + }, + { + "accuracy": 0.736555, + "ap": 0.6802131805554019, + "ap_weighted": 0.6802131805554019, + "f1": 0.7359401246910472, + "f1_weighted": 0.7359401246910472 + }, + { + "accuracy": 0.65907, + "ap": 0.6066532921967269, + "ap_weighted": 0.6066532921967269, + "f1": 0.6586877623003314, + "f1_weighted": 0.6586877623003313 + }, + { + "accuracy": 0.63907, + "ap": 0.5840529066642646, + "ap_weighted": 0.5840529066642646, + "f1": 0.6288309727480417, + "f1_weighted": 0.6288309727480416 + }, + { + "accuracy": 0.696175, + "ap": 0.6592946865656213, + "ap_weighted": 0.6592946865656213, + "f1": 0.685333224077756, + "f1_weighted": 0.685333224077756 + }, + { + "accuracy": 0.6200525, + "ap": 0.5740974159153149, + "ap_weighted": 0.5740974159153149, + "f1": 0.6199965644229164, + "f1_weighted": 0.6199965644229164 + }, + { + "accuracy": 0.6400975, + "ap": 0.5883910870819724, + "ap_weighted": 0.5883910870819724, + "f1": 0.6396553839093924, + "f1_weighted": 0.6396553839093924 + } + ] + } + ] + }, + "task_name": "AmazonPolarityClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonReviewsClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonReviewsClassification.json new file mode 100644 index 000000000..7275efd78 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AmazonReviewsClassification.json @@ -0,0 +1,73 @@ +{ + "dataset_revision": "1399c76144fd37290681b995c656ef9b2e06e26d", + "evaluation_time": 13.751401424407959, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.33256, + "f1": 0.329834021844663, + "f1_weighted": 0.329834021844663, + "hf_subset": "en", + "languages": [ + "eng-Latn" + ], + "main_score": 0.33256, + "scores_per_experiment": [ + { + "accuracy": 0.3684, + "f1": 0.3585932746395291, + "f1_weighted": 0.3585932746395291 + }, + { + "accuracy": 0.3446, + "f1": 0.3442223672743794, + "f1_weighted": 0.3442223672743794 + }, + { + "accuracy": 0.3298, + "f1": 0.3285528766931936, + "f1_weighted": 0.32855287669319355 + }, + { + "accuracy": 0.3204, + "f1": 0.32472725024209953, + "f1_weighted": 0.32472725024209953 + }, + { + "accuracy": 0.3722, + "f1": 0.3597359132663452, + "f1_weighted": 0.35973591326634513 + }, + { + "accuracy": 0.3306, + "f1": 0.3258214584304595, + "f1_weighted": 0.3258214584304595 + }, + { + "accuracy": 0.2882, + "f1": 0.27992069615771664, + "f1_weighted": 0.2799206961577166 + }, + { + "accuracy": 0.351, + "f1": 0.3518605260392184, + "f1_weighted": 0.35186052603921836 + }, + { + "accuracy": 0.3332, + "f1": 0.3356947366029444, + "f1_weighted": 0.3356947366029444 + }, + { + "accuracy": 0.2872, + "f1": 0.2892111191007444, + "f1_weighted": 0.2892111191007444 + } + ] + } + ] + }, + "task_name": "AmazonReviewsClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringP2P.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringP2P.json new file mode 100644 index 000000000..1dd8919e0 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringP2P.json @@ -0,0 +1,46 @@ +{ + "dataset_revision": "0bbdb47bcbe3a90093699aefeed338a0f28a7ee8", + "evaluation_time": 5.34234356880188, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.5681659433257183, + "v_measure": 0.5681659433257183, + "v_measure_std": 0.0392844371028886, + "v_measures": { + "Level 0": [ + 0.571021860179227, + 0.558445102025693, + 0.5192942435542314, + 0.46692751901942636, + 0.5787954734441288, + 0.5328291596801524, + 0.5418081679739809, + 0.5087586862921119, + 0.5427002889670551, + 0.615271813446208 + ], + "Level 1": [ + 0.611635438747909, + 0.5768826830496762, + 0.6083908212160667, + 0.6174581813330922, + 0.5925718950823576, + 0.5799089503228464, + 0.5937753079301685, + 0.5914322436471388, + 0.5499037604298112, + 0.6055072701730871 + ] + } + } + ] + }, + "task_name": "ArXivHierarchicalClusteringP2P" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringS2S.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringS2S.json new file mode 100644 index 000000000..9a28bdfd4 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArXivHierarchicalClusteringS2S.json @@ -0,0 +1,46 @@ +{ + "dataset_revision": "b73bd54100e5abfa6e3a23dcafb46fe4d2438dc3", + "evaluation_time": 4.663327217102051, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.49948049993663013, + "v_measure": 0.49948049993663013, + "v_measure_std": 0.06500535974697143, + "v_measures": { + "Level 0": [ + 0.43507795195327875, + 0.44921526681592194, + 0.43747454911102507, + 0.4115123889965728, + 0.4377369510154872, + 0.4304015944243319, + 0.3905931709269928, + 0.4841635216435706, + 0.452931110787906, + 0.4571673882122582 + ], + "Level 1": [ + 0.5407642401070188, + 0.5838001784129931, + 0.5694912184778929, + 0.5541643887758453, + 0.5155055401910514, + 0.566695819183142, + 0.5580033009026639, + 0.5821946887978546, + 0.587939878883979, + 0.5447768511128162 + ] + } + } + ] + }, + "task_name": "ArXivHierarchicalClusteringS2S" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArguAna.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArguAna.json new file mode 100644 index 000000000..5138fd6c3 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArguAna.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "c22ab2a51041ffd869aaddef7af8d8215647e41a", + "evaluation_time": 56.297197341918945, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.35442, + "map_at_1": 0.14936, + "map_at_10": 0.27343, + "map_at_100": 0.28713, + "map_at_1000": 0.2875, + "map_at_20": 0.28229, + "map_at_3": 0.22392, + "map_at_5": 0.24881, + "mrr_at_1": 0.15220483641536273, + "mrr_at_10": 0.27442000270947603, + "mrr_at_100": 0.2881282523915685, + "mrr_at_1000": 0.2884982914822303, + "mrr_at_20": 0.2832801156075957, + "mrr_at_3": 0.2251066856330013, + "mrr_at_5": 0.25007112375533364, + "nauc_map_at_1000_diff1": 0.0778663450328989, + "nauc_map_at_1000_max": -0.034739307716056454, + "nauc_map_at_1000_std": 0.0009890331646639778, + "nauc_map_at_100_diff1": 0.07801107037431429, + "nauc_map_at_100_max": -0.03426270570925563, + "nauc_map_at_100_std": 0.0015013588673745922, + "nauc_map_at_10_diff1": 0.07666195343846416, + "nauc_map_at_10_max": -0.036543122558546234, + "nauc_map_at_10_std": -0.003203950002831948, + "nauc_map_at_1_diff1": 0.09877295443817387, + "nauc_map_at_1_max": -0.0814307908274425, + "nauc_map_at_1_std": -0.01986775951007785, + "nauc_map_at_20_diff1": 0.07875154490173226, + "nauc_map_at_20_max": -0.03244513453789733, + "nauc_map_at_20_std": 0.00069236995616282, + "nauc_map_at_3_diff1": 0.07374706896113054, + "nauc_map_at_3_max": -0.053796077518734844, + "nauc_map_at_3_std": -0.018636255651657725, + "nauc_map_at_5_diff1": 0.07136277204557652, + "nauc_map_at_5_max": -0.04365777965318043, + "nauc_map_at_5_std": -0.007507078324326316, + "nauc_mrr_at_1000_diff1": 0.06863028341369651, + "nauc_mrr_at_1000_max": -0.039171434906955106, + "nauc_mrr_at_1000_std": 0.0015777443898158912, + "nauc_mrr_at_100_diff1": 0.06878706888310114, + "nauc_mrr_at_100_max": -0.03869113857892444, + "nauc_mrr_at_100_std": 0.002086693591843196, + "nauc_mrr_at_10_diff1": 0.06773716002758336, + "nauc_mrr_at_10_max": -0.04081652997319575, + "nauc_mrr_at_10_std": -0.002615323021304616, + "nauc_mrr_at_1_diff1": 0.08524205401827067, + "nauc_mrr_at_1_max": -0.0848978934833052, + "nauc_mrr_at_1_std": -0.017030369577807142, + "nauc_mrr_at_20_diff1": 0.06965011085176623, + "nauc_mrr_at_20_max": -0.03681974824438021, + "nauc_mrr_at_20_std": 0.0012734067857509562, + "nauc_mrr_at_3_diff1": 0.06529691252716202, + "nauc_mrr_at_3_max": -0.059665239669784674, + "nauc_mrr_at_3_std": -0.01830544611352626, + "nauc_mrr_at_5_diff1": 0.06277582503824558, + "nauc_mrr_at_5_max": -0.048767745834423816, + "nauc_mrr_at_5_std": -0.006974713042325226, + "nauc_ndcg_at_1000_diff1": 0.08162042025375826, + "nauc_ndcg_at_1000_max": -0.015767709007327244, + "nauc_ndcg_at_1000_std": 0.01822780552086109, + "nauc_ndcg_at_100_diff1": 0.08519562936565743, + "nauc_ndcg_at_100_max": -0.003104985312561409, + "nauc_ndcg_at_100_std": 0.03354046376185884, + "nauc_ndcg_at_10_diff1": 0.07916539124289947, + "nauc_ndcg_at_10_max": -0.010749020052134144, + "nauc_ndcg_at_10_std": 0.009317238748243677, + "nauc_ndcg_at_1_diff1": 0.09877295443817387, + "nauc_ndcg_at_1_max": -0.0814307908274425, + "nauc_ndcg_at_1_std": -0.01986775951007785, + "nauc_ndcg_at_20_diff1": 0.08804218306909174, + "nauc_ndcg_at_20_max": 0.00551702949338074, + "nauc_ndcg_at_20_std": 0.023578268166237943, + "nauc_ndcg_at_3_diff1": 0.06998386723183851, + "nauc_ndcg_at_3_max": -0.04568718881847778, + "nauc_ndcg_at_3_std": -0.021368507574166175, + "nauc_ndcg_at_5_diff1": 0.06666074859829946, + "nauc_ndcg_at_5_max": -0.02756737626670596, + "nauc_ndcg_at_5_std": -0.0013591316658041498, + "nauc_precision_at_1000_diff1": 0.323535687409865, + "nauc_precision_at_1000_max": 0.34567407416214996, + "nauc_precision_at_1000_std": 0.6754661258225708, + "nauc_precision_at_100_diff1": 0.19932446465866815, + "nauc_precision_at_100_max": 0.32735600878707954, + "nauc_precision_at_100_std": 0.4735792643210791, + "nauc_precision_at_10_diff1": 0.0918463777787202, + "nauc_precision_at_10_max": 0.06761453606135101, + "nauc_precision_at_10_std": 0.049793580551195954, + "nauc_precision_at_1_diff1": 0.09877295443817387, + "nauc_precision_at_1_max": -0.0814307908274425, + "nauc_precision_at_1_std": -0.01986775951007785, + "nauc_precision_at_20_diff1": 0.1395467684010704, + "nauc_precision_at_20_max": 0.1670041128937226, + "nauc_precision_at_20_std": 0.12673950222694627, + "nauc_precision_at_3_diff1": 0.061768145541080434, + "nauc_precision_at_3_max": -0.02625464093462827, + "nauc_precision_at_3_std": -0.02860973962125212, + "nauc_precision_at_5_diff1": 0.056403052255293525, + "nauc_precision_at_5_max": 0.012794816692743913, + "nauc_precision_at_5_std": 0.015137191038009163, + "nauc_recall_at_1000_diff1": 0.3235356874098673, + "nauc_recall_at_1000_max": 0.34567407416215784, + "nauc_recall_at_1000_std": 0.6754661258225653, + "nauc_recall_at_100_diff1": 0.1993244646586685, + "nauc_recall_at_100_max": 0.3273560087870795, + "nauc_recall_at_100_std": 0.47357926432107983, + "nauc_recall_at_10_diff1": 0.09184637777871996, + "nauc_recall_at_10_max": 0.06761453606135086, + "nauc_recall_at_10_std": 0.04979358055119591, + "nauc_recall_at_1_diff1": 0.09877295443817387, + "nauc_recall_at_1_max": -0.0814307908274425, + "nauc_recall_at_1_std": -0.01986775951007785, + "nauc_recall_at_20_diff1": 0.13954676840107105, + "nauc_recall_at_20_max": 0.16700411289372227, + "nauc_recall_at_20_std": 0.12673950222694566, + "nauc_recall_at_3_diff1": 0.06176814554108066, + "nauc_recall_at_3_max": -0.02625464093462808, + "nauc_recall_at_3_std": -0.02860973962125198, + "nauc_recall_at_5_diff1": 0.05640305225529333, + "nauc_recall_at_5_max": 0.012794816692743592, + "nauc_recall_at_5_std": 0.015137191038008977, + "ndcg_at_1": 0.14936, + "ndcg_at_10": 0.35442, + "ndcg_at_100": 0.41922, + "ndcg_at_1000": 0.42829, + "ndcg_at_20": 0.38582, + "ndcg_at_3": 0.24943, + "ndcg_at_5": 0.29442, + "precision_at_1": 0.14936, + "precision_at_10": 0.06195, + "precision_at_100": 0.00918, + "precision_at_1000": 0.00099, + "precision_at_20": 0.03709, + "precision_at_3": 0.10787, + "precision_at_5": 0.08663, + "recall_at_1": 0.14936, + "recall_at_10": 0.61949, + "recall_at_100": 0.91821, + "recall_at_1000": 0.98791, + "recall_at_20": 0.74182, + "recall_at_3": 0.32361, + "recall_at_5": 0.43314 + } + ] + }, + "task_name": "ArguAna" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArxivClusteringP2P.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArxivClusteringP2P.json new file mode 100644 index 000000000..adbb11a21 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ArxivClusteringP2P.json @@ -0,0 +1,53 @@ +{ + "dataset_revision": "a122ad7f3f0291bf49cc6f4d32aa80929df69d5d", + "evaluation_time": 4285.0073301792145, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.380074150423042, + "v_measure": 0.380074150423042, + "v_measure_std": 0.14351446727322215, + "v_measures": [ + 0.3684126058907928, + 0.4019205261862912, + 0.408494234961365, + 0.39183753770256363, + 0.3579862873771876, + 0.390749559334742, + 0.37658038688098944, + 0.3844555812299548, + 0.39032623255195437, + 0.3996697778972331, + 0.43669759090069665, + 0.44098088848888, + 0.4413129463094266, + 0.44345143811222687, + 0.440593131631622, + 0.4435254382939257, + 0.4382002597069241, + 0.4438167109679768, + 0.4411810105414298, + 0.4371303194979269, + 0.4046498970329238, + 0.24242698243292507, + 0.27583068597847404, + 0.3050927297826348, + 0.2784567642330301, + 0.19654433349410058, + 0.25387911853351197, + 0.15390088943901814, + 0.17967933501158162, + 1.0, + 0.21451546271198937 + ] + } + ] + }, + "task_name": "ArxivClusteringP2P" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AskUbuntuDupQuestions.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AskUbuntuDupQuestions.json new file mode 100644 index 000000000..b0ae1bc4e --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/AskUbuntuDupQuestions.json @@ -0,0 +1,26 @@ +{ + "dataset_revision": "2000358ca161889fa9c082cb41daa8dcfb161a54", + "evaluation_time": 3.6579322814941406, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.5227435199495557, + "map": 0.5227435199495557, + "mrr": 0.6556731741634789, + "nAUC_map_diff1": 0.09603573383700979, + "nAUC_map_max": 0.20737751123000678, + "nAUC_map_std": 0.12385001867066768, + "nAUC_mrr_diff1": 0.08771263792334094, + "nAUC_mrr_max": 0.27462664704691353, + "nAUC_mrr_std": 0.12668815821434576 + } + ] + }, + "task_name": "AskUbuntuDupQuestions" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BIOSSES.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BIOSSES.json new file mode 100644 index 000000000..3646d20da --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BIOSSES.json @@ -0,0 +1,26 @@ +{ + "dataset_revision": "d3fb88f8f02e40887cd149695127462bbcf29b4a", + "evaluation_time": 0.3543992042541504, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "cosine_pearson": 0.7648855620304972, + "cosine_spearman": 0.7077631148145085, + "euclidean_pearson": 0.750123264686467, + "euclidean_spearman": 0.709666772648475, + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7077631148145085, + "manhattan_pearson": 0.7503731636397172, + "manhattan_spearman": 0.7097029180503859, + "pearson": 0.7648855620304972, + "spearman": 0.7077631148145085 + } + ] + }, + "task_name": "BIOSSES" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/Banking77Classification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/Banking77Classification.json new file mode 100644 index 000000000..b3d898bcb --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/Banking77Classification.json @@ -0,0 +1,73 @@ +{ + "dataset_revision": "0fd18e25b25c072e09e0d92ab615fda904d66300", + "evaluation_time": 16.587544918060303, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.7231818181818183, + "f1": 0.7228983655466756, + "f1_weighted": 0.7228983655466757, + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.7231818181818183, + "scores_per_experiment": [ + { + "accuracy": 0.7253246753246754, + "f1": 0.7254443088410392, + "f1_weighted": 0.7254443088410392 + }, + { + "accuracy": 0.7113636363636363, + "f1": 0.7115623813678859, + "f1_weighted": 0.7115623813678861 + }, + { + "accuracy": 0.7428571428571429, + "f1": 0.7428410650788556, + "f1_weighted": 0.7428410650788557 + }, + { + "accuracy": 0.7301948051948052, + "f1": 0.730624655118211, + "f1_weighted": 0.730624655118211 + }, + { + "accuracy": 0.7201298701298702, + "f1": 0.7201267495470597, + "f1_weighted": 0.7201267495470598 + }, + { + "accuracy": 0.7224025974025974, + "f1": 0.7209432006996159, + "f1_weighted": 0.720943200699616 + }, + { + "accuracy": 0.7253246753246754, + "f1": 0.7254725296849156, + "f1_weighted": 0.7254725296849158 + }, + { + "accuracy": 0.7175324675324676, + "f1": 0.7161049661832862, + "f1_weighted": 0.7161049661832862 + }, + { + "accuracy": 0.7282467532467533, + "f1": 0.7267750616107864, + "f1_weighted": 0.7267750616107865 + }, + { + "accuracy": 0.7084415584415584, + "f1": 0.7090887373351012, + "f1_weighted": 0.7090887373351014 + } + ] + } + ] + }, + "task_name": "Banking77Classification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BiorxivClusteringP2P.v2.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BiorxivClusteringP2P.v2.json new file mode 100644 index 000000000..c06471ecf --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/BiorxivClusteringP2P.v2.json @@ -0,0 +1,34 @@ +{ + "dataset_revision": "f5dbc242e11dd8e24def4c4268607a49e02946dc", + "evaluation_time": 23.796001195907593, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.3287646605852736, + "v_measure": 0.3287646605852736, + "v_measure_std": 0.006989015876304395, + "v_measures": { + "Level 0": [ + 0.33267304083579735, + 0.33852922368360466, + 0.3290566812131874, + 0.3349920570287065, + 0.3247715459506535, + 0.33238153700837314, + 0.327619748553818, + 0.33376655587742554, + 0.31823406671226784, + 0.3156221489889018 + ] + } + } + ] + }, + "task_name": "BiorxivClusteringP2P.v2" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackGamingRetrieval.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackGamingRetrieval.json new file mode 100644 index 000000000..088d4973b --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackGamingRetrieval.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "4885aa143210c98657558c04aaf3dc47cfb54340", + "evaluation_time": 149.36014246940613, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.35282, + "map_at_1": 0.23442, + "map_at_10": 0.3105, + "map_at_100": 0.32064, + "map_at_1000": 0.32159, + "map_at_20": 0.31603, + "map_at_3": 0.28946, + "map_at_5": 0.30127, + "mrr_at_1": 0.26959247648902823, + "mrr_at_10": 0.34135841170323894, + "mrr_at_100": 0.3498349605064726, + "mrr_at_1000": 0.35050078473734514, + "mrr_at_20": 0.3461691122322251, + "mrr_at_3": 0.32142110762800385, + "mrr_at_5": 0.33308254963427336, + "nauc_map_at_1000_diff1": 0.41958486003300316, + "nauc_map_at_1000_max": 0.2894052816290465, + "nauc_map_at_1000_std": -0.03650482175085037, + "nauc_map_at_100_diff1": 0.41956298475724213, + "nauc_map_at_100_max": 0.2895182423957622, + "nauc_map_at_100_std": -0.03651040517035734, + "nauc_map_at_10_diff1": 0.41975466359387065, + "nauc_map_at_10_max": 0.287056792514622, + "nauc_map_at_10_std": -0.04151640066555949, + "nauc_map_at_1_diff1": 0.4758389835063324, + "nauc_map_at_1_max": 0.2440245689161278, + "nauc_map_at_1_std": -0.07707661115743089, + "nauc_map_at_20_diff1": 0.4196995812668938, + "nauc_map_at_20_max": 0.28829174006056735, + "nauc_map_at_20_std": -0.03924846157667851, + "nauc_map_at_3_diff1": 0.4317830348854507, + "nauc_map_at_3_max": 0.2756381008587014, + "nauc_map_at_3_std": -0.056367233051213377, + "nauc_map_at_5_diff1": 0.42625947409277853, + "nauc_map_at_5_max": 0.28306894879610284, + "nauc_map_at_5_std": -0.04668808871793209, + "nauc_mrr_at_1000_diff1": 0.41865788449462216, + "nauc_mrr_at_1000_max": 0.29807762300876595, + "nauc_mrr_at_1000_std": -0.016517106215868344, + "nauc_mrr_at_100_diff1": 0.4184692311656783, + "nauc_mrr_at_100_max": 0.29824316375446985, + "nauc_mrr_at_100_std": -0.01637338425960507, + "nauc_mrr_at_10_diff1": 0.4183258789879257, + "nauc_mrr_at_10_max": 0.2974207458830779, + "nauc_mrr_at_10_std": -0.018858373470847133, + "nauc_mrr_at_1_diff1": 0.47369309400557846, + "nauc_mrr_at_1_max": 0.27079148612980275, + "nauc_mrr_at_1_std": -0.051364270497058294, + "nauc_mrr_at_20_diff1": 0.4184682853355896, + "nauc_mrr_at_20_max": 0.29771632832498046, + "nauc_mrr_at_20_std": -0.018078523860094394, + "nauc_mrr_at_3_diff1": 0.429021697449899, + "nauc_mrr_at_3_max": 0.2910257123533071, + "nauc_mrr_at_3_std": -0.029341191054129565, + "nauc_mrr_at_5_diff1": 0.4247364383457092, + "nauc_mrr_at_5_max": 0.2975607749172641, + "nauc_mrr_at_5_std": -0.020666857373811222, + "nauc_ndcg_at_1000_diff1": 0.39807093360680346, + "nauc_ndcg_at_1000_max": 0.30802872182466606, + "nauc_ndcg_at_1000_std": 0.0009863037207928404, + "nauc_ndcg_at_100_diff1": 0.395137659680958, + "nauc_ndcg_at_100_max": 0.3113439199780419, + "nauc_ndcg_at_100_std": 0.0025642031325801844, + "nauc_ndcg_at_10_diff1": 0.3969076464797141, + "nauc_ndcg_at_10_max": 0.300973754038395, + "nauc_ndcg_at_10_std": -0.021179131346806858, + "nauc_ndcg_at_1_diff1": 0.47369309400557846, + "nauc_ndcg_at_1_max": 0.27079148612980275, + "nauc_ndcg_at_1_std": -0.051364270497058294, + "nauc_ndcg_at_20_diff1": 0.39605779251449325, + "nauc_ndcg_at_20_max": 0.30436992022864584, + "nauc_ndcg_at_20_std": -0.014401863963092716, + "nauc_ndcg_at_3_diff1": 0.419309294940883, + "nauc_ndcg_at_3_max": 0.2865336947866, + "nauc_ndcg_at_3_std": -0.04283731884074578, + "nauc_ndcg_at_5_diff1": 0.412308121517142, + "nauc_ndcg_at_5_max": 0.2962366683964995, + "nauc_ndcg_at_5_std": -0.029033621853864777, + "nauc_precision_at_1000_diff1": 0.015283257157466397, + "nauc_precision_at_1000_max": 0.1595277439643261, + "nauc_precision_at_1000_std": 0.16173311387938796, + "nauc_precision_at_100_diff1": 0.12400666573364458, + "nauc_precision_at_100_max": 0.2718097773372298, + "nauc_precision_at_100_std": 0.17203242644195202, + "nauc_precision_at_10_diff1": 0.24732717690644615, + "nauc_precision_at_10_max": 0.3403849749155897, + "nauc_precision_at_10_std": 0.08087743807754806, + "nauc_precision_at_1_diff1": 0.47369309400557846, + "nauc_precision_at_1_max": 0.27079148612980275, + "nauc_precision_at_1_std": -0.051364270497058294, + "nauc_precision_at_20_diff1": 0.2094733199868285, + "nauc_precision_at_20_max": 0.3145448629010409, + "nauc_precision_at_20_std": 0.10691934790755417, + "nauc_precision_at_3_diff1": 0.35241559074911694, + "nauc_precision_at_3_max": 0.3211192114370798, + "nauc_precision_at_3_std": 0.0032686719530984204, + "nauc_precision_at_5_diff1": 0.31568177352325105, + "nauc_precision_at_5_max": 0.34205408694917905, + "nauc_precision_at_5_std": 0.0496148620852961, + "nauc_recall_at_1000_diff1": 0.2598391009487387, + "nauc_recall_at_1000_max": 0.3702537774311658, + "nauc_recall_at_1000_std": 0.23081465620476987, + "nauc_recall_at_100_diff1": 0.2883094958837044, + "nauc_recall_at_100_max": 0.3693282788094915, + "nauc_recall_at_100_std": 0.1438017400462472, + "nauc_recall_at_10_diff1": 0.3192791221097442, + "nauc_recall_at_10_max": 0.3131321164895777, + "nauc_recall_at_10_std": 0.011923367173439984, + "nauc_recall_at_1_diff1": 0.4758389835063324, + "nauc_recall_at_1_max": 0.2440245689161278, + "nauc_recall_at_1_std": -0.07707661115743089, + "nauc_recall_at_20_diff1": 0.3082339909581201, + "nauc_recall_at_20_max": 0.32388426064735043, + "nauc_recall_at_20_std": 0.037845651347116115, + "nauc_recall_at_3_diff1": 0.3869039581092323, + "nauc_recall_at_3_max": 0.2875130847050974, + "nauc_recall_at_3_std": -0.038398850207808616, + "nauc_recall_at_5_diff1": 0.36559499405296797, + "nauc_recall_at_5_max": 0.30783683017200003, + "nauc_recall_at_5_std": -0.007002480438853385, + "ndcg_at_1": 0.26959, + "ndcg_at_10": 0.35282, + "ndcg_at_100": 0.40084, + "ndcg_at_1000": 0.42537, + "ndcg_at_20": 0.37138, + "ndcg_at_3": 0.31386, + "ndcg_at_5": 0.33272, + "precision_at_1": 0.26959, + "precision_at_10": 0.05661, + "precision_at_100": 0.00887, + "precision_at_1000": 0.00117, + "precision_at_20": 0.03348, + "precision_at_3": 0.13856, + "precision_at_5": 0.09618, + "recall_at_1": 0.23442, + "recall_at_10": 0.45053, + "recall_at_100": 0.66571, + "recall_at_1000": 0.84824, + "recall_at_20": 0.52029, + "recall_at_3": 0.34495, + "recall_at_5": 0.39239 + } + ] + }, + "task_name": "CQADupstackGamingRetrieval" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackUnixRetrieval.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackUnixRetrieval.json new file mode 100644 index 000000000..4f82e9fd9 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/CQADupstackUnixRetrieval.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "6c6430d3a6d36f8d2a829195bc5dc94d7e063e53", + "evaluation_time": 403.16394209861755, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.20605, + "map_at_1": 0.13745, + "map_at_10": 0.17813, + "map_at_100": 0.18569, + "map_at_1000": 0.18688, + "map_at_20": 0.18211, + "map_at_3": 0.1652, + "map_at_5": 0.1718, + "mrr_at_1": 0.15858208955223882, + "mrr_at_10": 0.20439321250888404, + "mrr_at_100": 0.2119536462498243, + "mrr_at_1000": 0.2128943218125713, + "mrr_at_20": 0.20863100630122713, + "mrr_at_3": 0.1901430348258707, + "mrr_at_5": 0.19741915422885573, + "nauc_map_at_1000_diff1": 0.4340564825978923, + "nauc_map_at_1000_max": 0.2738798752283611, + "nauc_map_at_1000_std": 0.07739905555470891, + "nauc_map_at_100_diff1": 0.4341548025169717, + "nauc_map_at_100_max": 0.2734556288496839, + "nauc_map_at_100_std": 0.07652157841238504, + "nauc_map_at_10_diff1": 0.44080056343594903, + "nauc_map_at_10_max": 0.2758257305913429, + "nauc_map_at_10_std": 0.07543849535554786, + "nauc_map_at_1_diff1": 0.5260373631218992, + "nauc_map_at_1_max": 0.285905790778449, + "nauc_map_at_1_std": 0.04127111756492736, + "nauc_map_at_20_diff1": 0.4366085441450429, + "nauc_map_at_20_max": 0.2743130189317691, + "nauc_map_at_20_std": 0.07538751159446563, + "nauc_map_at_3_diff1": 0.45628836034272385, + "nauc_map_at_3_max": 0.2756692560044045, + "nauc_map_at_3_std": 0.06553902330601845, + "nauc_map_at_5_diff1": 0.4495989655618646, + "nauc_map_at_5_max": 0.27841803621177796, + "nauc_map_at_5_std": 0.07926883045099871, + "nauc_mrr_at_1000_diff1": 0.4175028827717999, + "nauc_mrr_at_1000_max": 0.2793858816840362, + "nauc_mrr_at_1000_std": 0.08401042545714836, + "nauc_mrr_at_100_diff1": 0.4174204688611061, + "nauc_mrr_at_100_max": 0.27923956275626804, + "nauc_mrr_at_100_std": 0.08345077643301863, + "nauc_mrr_at_10_diff1": 0.4239957031607702, + "nauc_mrr_at_10_max": 0.28210868697439584, + "nauc_mrr_at_10_std": 0.0836232388443917, + "nauc_mrr_at_1_diff1": 0.5108296297391117, + "nauc_mrr_at_1_max": 0.28493122931874637, + "nauc_mrr_at_1_std": 0.054414508391988935, + "nauc_mrr_at_20_diff1": 0.41927408743653605, + "nauc_mrr_at_20_max": 0.2805584194585427, + "nauc_mrr_at_20_std": 0.08357285365193758, + "nauc_mrr_at_3_diff1": 0.4415971796982716, + "nauc_mrr_at_3_max": 0.2832795489010544, + "nauc_mrr_at_3_std": 0.07456561822853007, + "nauc_mrr_at_5_diff1": 0.43310817882766217, + "nauc_mrr_at_5_max": 0.28590021907819385, + "nauc_mrr_at_5_std": 0.0872354698274638, + "nauc_ndcg_at_1000_diff1": 0.37532783940795095, + "nauc_ndcg_at_1000_max": 0.27194456133517486, + "nauc_ndcg_at_1000_std": 0.10907909849113337, + "nauc_ndcg_at_100_diff1": 0.37947456764720056, + "nauc_ndcg_at_100_max": 0.2625191356017194, + "nauc_ndcg_at_100_std": 0.09025154007971704, + "nauc_ndcg_at_10_diff1": 0.40580600194063643, + "nauc_ndcg_at_10_max": 0.27330330471530645, + "nauc_ndcg_at_10_std": 0.08609992103501417, + "nauc_ndcg_at_1_diff1": 0.5108296297391117, + "nauc_ndcg_at_1_max": 0.28493122931874637, + "nauc_ndcg_at_1_std": 0.054414508391988935, + "nauc_ndcg_at_20_diff1": 0.3924500754857453, + "nauc_ndcg_at_20_max": 0.26782333698741617, + "nauc_ndcg_at_20_std": 0.08476651567705681, + "nauc_ndcg_at_3_diff1": 0.43680823279139425, + "nauc_ndcg_at_3_max": 0.2794104249785243, + "nauc_ndcg_at_3_std": 0.07469800022523065, + "nauc_ndcg_at_5_diff1": 0.4244298978783087, + "nauc_ndcg_at_5_max": 0.28124949933446525, + "nauc_ndcg_at_5_std": 0.0956020734069938, + "nauc_precision_at_1000_diff1": 0.026483685770834358, + "nauc_precision_at_1000_max": 0.19073906880031166, + "nauc_precision_at_1000_std": 0.13999013440804536, + "nauc_precision_at_100_diff1": 0.16870899908695963, + "nauc_precision_at_100_max": 0.23390971795944387, + "nauc_precision_at_100_std": 0.1204637399297324, + "nauc_precision_at_10_diff1": 0.2944310076482644, + "nauc_precision_at_10_max": 0.2769315020017141, + "nauc_precision_at_10_std": 0.11916411708526571, + "nauc_precision_at_1_diff1": 0.5108296297391117, + "nauc_precision_at_1_max": 0.28493122931874637, + "nauc_precision_at_1_std": 0.054414508391988935, + "nauc_precision_at_20_diff1": 0.24934949720827895, + "nauc_precision_at_20_max": 0.2555161857030095, + "nauc_precision_at_20_std": 0.11668636679060868, + "nauc_precision_at_3_diff1": 0.36485332551259037, + "nauc_precision_at_3_max": 0.28237452826682413, + "nauc_precision_at_3_std": 0.09954973931568155, + "nauc_precision_at_5_diff1": 0.33402160689464416, + "nauc_precision_at_5_max": 0.29082858014567947, + "nauc_precision_at_5_std": 0.1429650174650459, + "nauc_recall_at_1000_diff1": 0.14802681219724195, + "nauc_recall_at_1000_max": 0.2468630884357715, + "nauc_recall_at_1000_std": 0.2676057516422741, + "nauc_recall_at_100_diff1": 0.22722397829411736, + "nauc_recall_at_100_max": 0.19641080412252182, + "nauc_recall_at_100_std": 0.11001814742497579, + "nauc_recall_at_10_diff1": 0.32276624411190363, + "nauc_recall_at_10_max": 0.24862829626070926, + "nauc_recall_at_10_std": 0.09757364968651897, + "nauc_recall_at_1_diff1": 0.5260373631218992, + "nauc_recall_at_1_max": 0.285905790778449, + "nauc_recall_at_1_std": 0.04127111756492736, + "nauc_recall_at_20_diff1": 0.28062291188608607, + "nauc_recall_at_20_max": 0.227161402308901, + "nauc_recall_at_20_std": 0.08766932365570479, + "nauc_recall_at_3_diff1": 0.3938882050948329, + "nauc_recall_at_3_max": 0.2662639043754511, + "nauc_recall_at_3_std": 0.08224527245411063, + "nauc_recall_at_5_diff1": 0.3642314763683684, + "nauc_recall_at_5_max": 0.26862139308729827, + "nauc_recall_at_5_std": 0.1257383003509626, + "ndcg_at_1": 0.15858, + "ndcg_at_10": 0.20605, + "ndcg_at_100": 0.2464, + "ndcg_at_1000": 0.27983, + "ndcg_at_20": 0.2201, + "ndcg_at_3": 0.1808, + "ndcg_at_5": 0.19139, + "precision_at_1": 0.15858, + "precision_at_10": 0.03377, + "precision_at_100": 0.00603, + "precision_at_1000": 0.001, + "precision_at_20": 0.02029, + "precision_at_3": 0.0796, + "precision_at_5": 0.05522, + "recall_at_1": 0.13745, + "recall_at_10": 0.26538, + "recall_at_100": 0.45124, + "recall_at_1000": 0.69957, + "recall_at_20": 0.31738, + "recall_at_3": 0.19666, + "recall_at_5": 0.22357 + } + ] + }, + "task_name": "CQADupstackUnixRetrieval" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ClimateFEVERHardNegatives.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ClimateFEVERHardNegatives.json new file mode 100644 index 000000000..8a1d6e44e --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ClimateFEVERHardNegatives.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "3a309e201f3c2c4b13bd4a367a8f37eee2ec1d21", + "evaluation_time": 346.9498734474182, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13782, + "map_at_1": 0.04743, + "map_at_10": 0.08978, + "map_at_100": 0.10285, + "map_at_1000": 0.10507, + "map_at_20": 0.09596, + "map_at_3": 0.07253, + "map_at_5": 0.08101, + "mrr_at_1": 0.1, + "mrr_at_10": 0.17760873015873016, + "mrr_at_100": 0.1904583685679413, + "mrr_at_1000": 0.19132487995654088, + "mrr_at_20": 0.18485909377859858, + "mrr_at_3": 0.14799999999999996, + "mrr_at_5": 0.16405000000000006, + "nauc_map_at_1000_diff1": 0.12522107130021887, + "nauc_map_at_1000_max": 0.22372842499616918, + "nauc_map_at_1000_std": 0.11705874268114085, + "nauc_map_at_100_diff1": 0.12615324156649307, + "nauc_map_at_100_max": 0.22176724918464324, + "nauc_map_at_100_std": 0.1148999818394875, + "nauc_map_at_10_diff1": 0.12820876229435454, + "nauc_map_at_10_max": 0.20159475339702285, + "nauc_map_at_10_std": 0.09561664869494926, + "nauc_map_at_1_diff1": 0.24455253406180538, + "nauc_map_at_1_max": 0.1645283388149118, + "nauc_map_at_1_std": 0.06336299978825388, + "nauc_map_at_20_diff1": 0.12884695467706417, + "nauc_map_at_20_max": 0.2153443338638166, + "nauc_map_at_20_std": 0.10692635295302387, + "nauc_map_at_3_diff1": 0.1402115548227943, + "nauc_map_at_3_max": 0.16711581532841824, + "nauc_map_at_3_std": 0.05814279135179269, + "nauc_map_at_5_diff1": 0.13100412245912882, + "nauc_map_at_5_max": 0.1827698099845315, + "nauc_map_at_5_std": 0.07919000991411358, + "nauc_mrr_at_1000_diff1": 0.10710745088060997, + "nauc_mrr_at_1000_max": 0.25706844196931017, + "nauc_mrr_at_1000_std": 0.13897216576308308, + "nauc_mrr_at_100_diff1": 0.10710624120873036, + "nauc_mrr_at_100_max": 0.25733053975865167, + "nauc_mrr_at_100_std": 0.1392140920930256, + "nauc_mrr_at_10_diff1": 0.10695539587719081, + "nauc_mrr_at_10_max": 0.25080510351555996, + "nauc_mrr_at_10_std": 0.13397422019188945, + "nauc_mrr_at_1_diff1": 0.15341561577676407, + "nauc_mrr_at_1_max": 0.21574188355245497, + "nauc_mrr_at_1_std": 0.09334853769788033, + "nauc_mrr_at_20_diff1": 0.10839681170521953, + "nauc_mrr_at_20_max": 0.25709270719835325, + "nauc_mrr_at_20_std": 0.1394828617640488, + "nauc_mrr_at_3_diff1": 0.11713922022823264, + "nauc_mrr_at_3_max": 0.23110644442429404, + "nauc_mrr_at_3_std": 0.10580659033267667, + "nauc_mrr_at_5_diff1": 0.107953062343631, + "nauc_mrr_at_5_max": 0.2384625951327732, + "nauc_mrr_at_5_std": 0.12075269199700465, + "nauc_ndcg_at_1000_diff1": 0.07597371143350067, + "nauc_ndcg_at_1000_max": 0.3065896217594407, + "nauc_ndcg_at_1000_std": 0.20030218109698567, + "nauc_ndcg_at_100_diff1": 0.0915952637104663, + "nauc_ndcg_at_100_max": 0.2838419150417237, + "nauc_ndcg_at_100_std": 0.1802846188436026, + "nauc_ndcg_at_10_diff1": 0.09912576916121484, + "nauc_ndcg_at_10_max": 0.23777407235743414, + "nauc_ndcg_at_10_std": 0.13376580600411314, + "nauc_ndcg_at_1_diff1": 0.15341561577676407, + "nauc_ndcg_at_1_max": 0.21574188355245497, + "nauc_ndcg_at_1_std": 0.09334853769788033, + "nauc_ndcg_at_20_diff1": 0.102833591507714, + "nauc_ndcg_at_20_max": 0.2655396923955338, + "nauc_ndcg_at_20_std": 0.15804805394075924, + "nauc_ndcg_at_3_diff1": 0.11179196457349776, + "nauc_ndcg_at_3_max": 0.19194990316901736, + "nauc_ndcg_at_3_std": 0.07656296797184103, + "nauc_ndcg_at_5_diff1": 0.1008193569107808, + "nauc_ndcg_at_5_max": 0.20566710335976515, + "nauc_ndcg_at_5_std": 0.10438610392866259, + "nauc_precision_at_1000_diff1": -0.06607952090874046, + "nauc_precision_at_1000_max": 0.3362729910047398, + "nauc_precision_at_1000_std": 0.24799665464257992, + "nauc_precision_at_100_diff1": 0.00866726055963123, + "nauc_precision_at_100_max": 0.35407242153272755, + "nauc_precision_at_100_std": 0.2569520556223409, + "nauc_precision_at_10_diff1": 0.03150979698183688, + "nauc_precision_at_10_max": 0.33402079128889417, + "nauc_precision_at_10_std": 0.21401717672219076, + "nauc_precision_at_1_diff1": 0.15341561577676407, + "nauc_precision_at_1_max": 0.21574188355245497, + "nauc_precision_at_1_std": 0.09334853769788033, + "nauc_precision_at_20_diff1": 0.04935136493923009, + "nauc_precision_at_20_max": 0.38137437944042024, + "nauc_precision_at_20_std": 0.25977622109859755, + "nauc_precision_at_3_diff1": 0.04601755923727957, + "nauc_precision_at_3_max": 0.23413130630954238, + "nauc_precision_at_3_std": 0.09850272297501178, + "nauc_precision_at_5_diff1": 0.025581749701208908, + "nauc_precision_at_5_max": 0.2711225019403562, + "nauc_precision_at_5_std": 0.15553322889535415, + "nauc_recall_at_1000_diff1": -0.05354753869625043, + "nauc_recall_at_1000_max": 0.3648111180014618, + "nauc_recall_at_1000_std": 0.3177421376223183, + "nauc_recall_at_100_diff1": 0.036044706486069424, + "nauc_recall_at_100_max": 0.2732123625883144, + "nauc_recall_at_100_std": 0.21737454943449647, + "nauc_recall_at_10_diff1": 0.06100859886113942, + "nauc_recall_at_10_max": 0.22331089142976837, + "nauc_recall_at_10_std": 0.14706943104675207, + "nauc_recall_at_1_diff1": 0.24455253406180538, + "nauc_recall_at_1_max": 0.1645283388149118, + "nauc_recall_at_1_std": 0.06336299978825388, + "nauc_recall_at_20_diff1": 0.06894460489569018, + "nauc_recall_at_20_max": 0.26599734866631436, + "nauc_recall_at_20_std": 0.1851422039194663, + "nauc_recall_at_3_diff1": 0.07044292809399187, + "nauc_recall_at_3_max": 0.1485750430632028, + "nauc_recall_at_3_std": 0.05853098982127944, + "nauc_recall_at_5_diff1": 0.06071131894476995, + "nauc_recall_at_5_max": 0.17806079802453179, + "nauc_recall_at_5_std": 0.10290341819974899, + "ndcg_at_1": 0.1, + "ndcg_at_10": 0.13782, + "ndcg_at_100": 0.20511, + "ndcg_at_1000": 0.25371, + "ndcg_at_20": 0.15971, + "ndcg_at_3": 0.10151, + "ndcg_at_5": 0.11496, + "precision_at_1": 0.1, + "precision_at_10": 0.0464, + "precision_at_100": 0.01183, + "precision_at_1000": 0.00208, + "precision_at_20": 0.03235, + "precision_at_3": 0.07667, + "precision_at_5": 0.0632, + "recall_at_1": 0.04743, + "recall_at_10": 0.18605, + "recall_at_100": 0.43108, + "recall_at_1000": 0.71157, + "recall_at_20": 0.24977, + "recall_at_3": 0.10127, + "recall_at_5": 0.13368 + } + ] + }, + "task_name": "ClimateFEVERHardNegatives" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FEVERHardNegatives.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FEVERHardNegatives.json new file mode 100644 index 000000000..0687e7c16 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FEVERHardNegatives.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "080c9ed6267b65029207906e815d44a9240bafca", + "evaluation_time": 746.5240535736084, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.29013, + "map_at_1": 0.16675, + "map_at_10": 0.24305, + "map_at_100": 0.25483, + "map_at_1000": 0.25562, + "map_at_20": 0.25052, + "map_at_3": 0.21816, + "map_at_5": 0.23174, + "mrr_at_1": 0.178, + "mrr_at_10": 0.25942976190476186, + "mrr_at_100": 0.2708245127742838, + "mrr_at_1000": 0.2715226783282931, + "mrr_at_20": 0.26692204777936207, + "mrr_at_3": 0.2341666666666668, + "mrr_at_5": 0.2480666666666667, + "nauc_map_at_1000_diff1": 0.21544854743509137, + "nauc_map_at_1000_max": 0.33687783701065527, + "nauc_map_at_1000_std": 0.19222550863102408, + "nauc_map_at_100_diff1": 0.21520468679380975, + "nauc_map_at_100_max": 0.3370716157823737, + "nauc_map_at_100_std": 0.19264691614646473, + "nauc_map_at_10_diff1": 0.21422215983726403, + "nauc_map_at_10_max": 0.3323775735953202, + "nauc_map_at_10_std": 0.18296345964132105, + "nauc_map_at_1_diff1": 0.282472252707504, + "nauc_map_at_1_max": 0.30869367866812353, + "nauc_map_at_1_std": 0.14892919510947344, + "nauc_map_at_20_diff1": 0.21479760376188198, + "nauc_map_at_20_max": 0.33487486921900306, + "nauc_map_at_20_std": 0.18734393192425947, + "nauc_map_at_3_diff1": 0.2414539739013598, + "nauc_map_at_3_max": 0.3040299248259469, + "nauc_map_at_3_std": 0.1473198851839032, + "nauc_map_at_5_diff1": 0.22327889608796098, + "nauc_map_at_5_max": 0.32197537030504264, + "nauc_map_at_5_std": 0.17166222717844512, + "nauc_mrr_at_1000_diff1": 0.21148841433112528, + "nauc_mrr_at_1000_max": 0.3382725467879975, + "nauc_mrr_at_1000_std": 0.19289276520465976, + "nauc_mrr_at_100_diff1": 0.21120813015263598, + "nauc_mrr_at_100_max": 0.33858946234586346, + "nauc_mrr_at_100_std": 0.19342593126301447, + "nauc_mrr_at_10_diff1": 0.21002673910238617, + "nauc_mrr_at_10_max": 0.3347351857713081, + "nauc_mrr_at_10_std": 0.18507781043013435, + "nauc_mrr_at_1_diff1": 0.27322048534309173, + "nauc_mrr_at_1_max": 0.3071828229456795, + "nauc_mrr_at_1_std": 0.15064782013214764, + "nauc_mrr_at_20_diff1": 0.2105171043976403, + "nauc_mrr_at_20_max": 0.3375869249205294, + "nauc_mrr_at_20_std": 0.18975718744201864, + "nauc_mrr_at_3_diff1": 0.23190785778386083, + "nauc_mrr_at_3_max": 0.3048324305479338, + "nauc_mrr_at_3_std": 0.1493372758907878, + "nauc_mrr_at_5_diff1": 0.2167296440467032, + "nauc_mrr_at_5_max": 0.3251310544093203, + "nauc_mrr_at_5_std": 0.17357779741682247, + "nauc_ndcg_at_1000_diff1": 0.18757208724489075, + "nauc_ndcg_at_1000_max": 0.3710457362118993, + "nauc_ndcg_at_1000_std": 0.2480753632757993, + "nauc_ndcg_at_100_diff1": 0.1831329318563014, + "nauc_ndcg_at_100_max": 0.37825810595474135, + "nauc_ndcg_at_100_std": 0.2592448792999036, + "nauc_ndcg_at_10_diff1": 0.17836214513063636, + "nauc_ndcg_at_10_max": 0.35804817898780755, + "nauc_ndcg_at_10_std": 0.21542151760192796, + "nauc_ndcg_at_1_diff1": 0.27322048534309173, + "nauc_ndcg_at_1_max": 0.3071828229456795, + "nauc_ndcg_at_1_std": 0.15064782013214764, + "nauc_ndcg_at_20_diff1": 0.1799208189963885, + "nauc_ndcg_at_20_max": 0.367036530596129, + "nauc_ndcg_at_20_std": 0.2312126033201478, + "nauc_ndcg_at_3_diff1": 0.2273157319844919, + "nauc_ndcg_at_3_max": 0.30318529128048305, + "nauc_ndcg_at_3_std": 0.14820077393258177, + "nauc_ndcg_at_5_diff1": 0.19777958340751806, + "nauc_ndcg_at_5_max": 0.3352169106934174, + "nauc_ndcg_at_5_std": 0.18999910579412774, + "nauc_precision_at_1000_diff1": -0.05109056979847481, + "nauc_precision_at_1000_max": 0.3412503595101295, + "nauc_precision_at_1000_std": 0.37960256573182904, + "nauc_precision_at_100_diff1": 0.025945385863158386, + "nauc_precision_at_100_max": 0.4750623700479704, + "nauc_precision_at_100_std": 0.4894022864631023, + "nauc_precision_at_10_diff1": 0.06951892452643185, + "nauc_precision_at_10_max": 0.4200099599469639, + "nauc_precision_at_10_std": 0.2974687434535927, + "nauc_precision_at_1_diff1": 0.27322048534309173, + "nauc_precision_at_1_max": 0.3071828229456795, + "nauc_precision_at_1_std": 0.15064782013214764, + "nauc_precision_at_20_diff1": 0.05661880739878372, + "nauc_precision_at_20_max": 0.44872073470443674, + "nauc_precision_at_20_std": 0.35956797309533034, + "nauc_precision_at_3_diff1": 0.18934408000700878, + "nauc_precision_at_3_max": 0.3026221973623029, + "nauc_precision_at_3_std": 0.15043905463416615, + "nauc_precision_at_5_diff1": 0.1300571668463389, + "nauc_precision_at_5_max": 0.3748354444813002, + "nauc_precision_at_5_std": 0.23534937598474137, + "nauc_recall_at_1000_diff1": 0.054114464460888204, + "nauc_recall_at_1000_max": 0.5158290911276654, + "nauc_recall_at_1000_std": 0.565918300833862, + "nauc_recall_at_100_diff1": 0.08060737315141657, + "nauc_recall_at_100_max": 0.5160207680012456, + "nauc_recall_at_100_std": 0.5142619474854602, + "nauc_recall_at_10_diff1": 0.08100436885404436, + "nauc_recall_at_10_max": 0.4134175714702475, + "nauc_recall_at_10_std": 0.2943702601091574, + "nauc_recall_at_1_diff1": 0.282472252707504, + "nauc_recall_at_1_max": 0.30869367866812353, + "nauc_recall_at_1_std": 0.14892919510947344, + "nauc_recall_at_20_diff1": 0.08116605583513638, + "nauc_recall_at_20_max": 0.4416664313227035, + "nauc_recall_at_20_std": 0.3481926911826832, + "nauc_recall_at_3_diff1": 0.19731556038907935, + "nauc_recall_at_3_max": 0.2941323001730545, + "nauc_recall_at_3_std": 0.14604038579374903, + "nauc_recall_at_5_diff1": 0.13243416677099187, + "nauc_recall_at_5_max": 0.35814857211035234, + "nauc_recall_at_5_std": 0.23300330758288532, + "ndcg_at_1": 0.178, + "ndcg_at_10": 0.29013, + "ndcg_at_100": 0.34584, + "ndcg_at_1000": 0.36811, + "ndcg_at_20": 0.31722, + "ndcg_at_3": 0.23883, + "ndcg_at_5": 0.26318, + "precision_at_1": 0.178, + "precision_at_10": 0.0459, + "precision_at_100": 0.00749, + "precision_at_1000": 0.00096, + "precision_at_20": 0.0288, + "precision_at_3": 0.10167, + "precision_at_5": 0.0736, + "recall_at_1": 0.16675, + "recall_at_10": 0.42243, + "recall_at_100": 0.67445, + "recall_at_1000": 0.84855, + "recall_at_20": 0.52725, + "recall_at_3": 0.28306, + "recall_at_5": 0.34159 + } + ] + }, + "task_name": "FEVERHardNegatives" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FiQA2018.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FiQA2018.json new file mode 100644 index 000000000..34c2fc2fa --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/FiQA2018.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "27a168819829fe9bcd655c2df245fb19452e8e06", + "evaluation_time": 294.45342993736267, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.13613, + "map_at_1": 0.05595, + "map_at_10": 0.0963, + "map_at_100": 0.10652, + "map_at_1000": 0.10826, + "map_at_20": 0.10164, + "map_at_3": 0.07969, + "map_at_5": 0.08864, + "mrr_at_1": 0.125, + "mrr_at_10": 0.17619353811483446, + "mrr_at_100": 0.18609274214218047, + "mrr_at_1000": 0.18710735865539185, + "mrr_at_20": 0.18214516308234066, + "mrr_at_3": 0.15637860082304522, + "mrr_at_5": 0.16772119341563788, + "nauc_map_at_1000_diff1": 0.31692450218783746, + "nauc_map_at_1000_max": 0.14324823990865673, + "nauc_map_at_1000_std": 0.14662690876318565, + "nauc_map_at_100_diff1": 0.3168034198464073, + "nauc_map_at_100_max": 0.1407086213058493, + "nauc_map_at_100_std": 0.14503532451716084, + "nauc_map_at_10_diff1": 0.32335819729805093, + "nauc_map_at_10_max": 0.14065260917478473, + "nauc_map_at_10_std": 0.12365145437363728, + "nauc_map_at_1_diff1": 0.3951569826310035, + "nauc_map_at_1_max": 0.18999982105646704, + "nauc_map_at_1_std": 0.07523857697259427, + "nauc_map_at_20_diff1": 0.31993792376410934, + "nauc_map_at_20_max": 0.13900685706361784, + "nauc_map_at_20_std": 0.1337316037418551, + "nauc_map_at_3_diff1": 0.33221672736092794, + "nauc_map_at_3_max": 0.16170345852042628, + "nauc_map_at_3_std": 0.11843849083870257, + "nauc_map_at_5_diff1": 0.32032432922074505, + "nauc_map_at_5_max": 0.14183582257951344, + "nauc_map_at_5_std": 0.10995198663430308, + "nauc_mrr_at_1000_diff1": 0.29809997054950776, + "nauc_mrr_at_1000_max": 0.17724394467555504, + "nauc_mrr_at_1000_std": 0.14697296533630105, + "nauc_mrr_at_100_diff1": 0.29794137934638604, + "nauc_mrr_at_100_max": 0.17678128306706994, + "nauc_mrr_at_100_std": 0.14678710317990853, + "nauc_mrr_at_10_diff1": 0.3001201245658097, + "nauc_mrr_at_10_max": 0.18246790532169166, + "nauc_mrr_at_10_std": 0.14476185164007396, + "nauc_mrr_at_1_diff1": 0.3768799510652951, + "nauc_mrr_at_1_max": 0.2049987465103496, + "nauc_mrr_at_1_std": 0.1251596394343786, + "nauc_mrr_at_20_diff1": 0.2983965774516374, + "nauc_mrr_at_20_max": 0.17677721836052632, + "nauc_mrr_at_20_std": 0.1438843997992953, + "nauc_mrr_at_3_diff1": 0.3134313208855489, + "nauc_mrr_at_3_max": 0.17845447399324968, + "nauc_mrr_at_3_std": 0.14066521833134218, + "nauc_mrr_at_5_diff1": 0.3004066423585125, + "nauc_mrr_at_5_max": 0.17853444460151383, + "nauc_mrr_at_5_std": 0.14473758937871994, + "nauc_ndcg_at_1000_diff1": 0.26459217354059944, + "nauc_ndcg_at_1000_max": 0.17387167351761004, + "nauc_ndcg_at_1000_std": 0.21056613586066858, + "nauc_ndcg_at_100_diff1": 0.2716164021618313, + "nauc_ndcg_at_100_max": 0.13909239071799773, + "nauc_ndcg_at_100_std": 0.19889333570622722, + "nauc_ndcg_at_10_diff1": 0.29233251903995133, + "nauc_ndcg_at_10_max": 0.14310564605195308, + "nauc_ndcg_at_10_std": 0.1411683425982775, + "nauc_ndcg_at_1_diff1": 0.3768799510652951, + "nauc_ndcg_at_1_max": 0.2049987465103496, + "nauc_ndcg_at_1_std": 0.1251596394343786, + "nauc_ndcg_at_20_diff1": 0.2841331954888152, + "nauc_ndcg_at_20_max": 0.13218242393559312, + "nauc_ndcg_at_20_std": 0.1544346744749663, + "nauc_ndcg_at_3_diff1": 0.3164350151672291, + "nauc_ndcg_at_3_max": 0.17211634315352872, + "nauc_ndcg_at_3_std": 0.13510336693215202, + "nauc_ndcg_at_5_diff1": 0.29341104586225963, + "nauc_ndcg_at_5_max": 0.1469377471098924, + "nauc_ndcg_at_5_std": 0.12684777919585524, + "nauc_precision_at_1000_diff1": 0.11675337776583926, + "nauc_precision_at_1000_max": 0.2642858375711761, + "nauc_precision_at_1000_std": 0.20117819447895613, + "nauc_precision_at_100_diff1": 0.1949643915135954, + "nauc_precision_at_100_max": 0.1902785710771811, + "nauc_precision_at_100_std": 0.2717380726473921, + "nauc_precision_at_10_diff1": 0.2781195989759886, + "nauc_precision_at_10_max": 0.1522765855242808, + "nauc_precision_at_10_std": 0.18954353251970057, + "nauc_precision_at_1_diff1": 0.3768799510652951, + "nauc_precision_at_1_max": 0.2049987465103496, + "nauc_precision_at_1_std": 0.1251596394343786, + "nauc_precision_at_20_diff1": 0.2508799026968985, + "nauc_precision_at_20_max": 0.15487570361092204, + "nauc_precision_at_20_std": 0.21204137408016688, + "nauc_precision_at_3_diff1": 0.2806482673730567, + "nauc_precision_at_3_max": 0.16704466727913292, + "nauc_precision_at_3_std": 0.16923235300425765, + "nauc_precision_at_5_diff1": 0.27447961182471475, + "nauc_precision_at_5_max": 0.1431484981353039, + "nauc_precision_at_5_std": 0.1639562080526267, + "nauc_recall_at_1000_diff1": 0.07632396161855513, + "nauc_recall_at_1000_max": 0.1893414731301623, + "nauc_recall_at_1000_std": 0.3254858671512196, + "nauc_recall_at_100_diff1": 0.15266007922141553, + "nauc_recall_at_100_max": 0.07310660304372543, + "nauc_recall_at_100_std": 0.26576733263061264, + "nauc_recall_at_10_diff1": 0.2170653806604956, + "nauc_recall_at_10_max": 0.09957272038136532, + "nauc_recall_at_10_std": 0.1310131241739144, + "nauc_recall_at_1_diff1": 0.3951569826310035, + "nauc_recall_at_1_max": 0.18999982105646704, + "nauc_recall_at_1_std": 0.07523857697259427, + "nauc_recall_at_20_diff1": 0.19768239567299542, + "nauc_recall_at_20_max": 0.06815912125318993, + "nauc_recall_at_20_std": 0.1504461284093666, + "nauc_recall_at_3_diff1": 0.26281823549872246, + "nauc_recall_at_3_max": 0.13564622782043995, + "nauc_recall_at_3_std": 0.14590947355742165, + "nauc_recall_at_5_diff1": 0.21019953648215856, + "nauc_recall_at_5_max": 0.0919353860543682, + "nauc_recall_at_5_std": 0.11526480891780816, + "ndcg_at_1": 0.125, + "ndcg_at_10": 0.13613, + "ndcg_at_100": 0.18657, + "ndcg_at_1000": 0.23013, + "ndcg_at_20": 0.15439, + "ndcg_at_3": 0.11216, + "ndcg_at_5": 0.12136, + "precision_at_1": 0.125, + "precision_at_10": 0.04182, + "precision_at_100": 0.00895, + "precision_at_1000": 0.00165, + "precision_at_20": 0.02731, + "precision_at_3": 0.07922, + "precision_at_5": 0.06235, + "recall_at_1": 0.05595, + "recall_at_10": 0.17588, + "recall_at_100": 0.37459, + "recall_at_1000": 0.65141, + "recall_at_20": 0.23593, + "recall_at_3": 0.09942, + "recall_at_5": 0.13211 + } + ] + }, + "task_name": "FiQA2018" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/HotpotQAHardNegatives.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/HotpotQAHardNegatives.json new file mode 100644 index 000000000..7667e0fbc --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/HotpotQAHardNegatives.json @@ -0,0 +1,158 @@ +{ + "dataset_revision": "617612fa63afcb60e3b134bed8b7216a99707c37", + "evaluation_time": 619.9214069843292, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.28296, + "map_at_1": 0.156, + "map_at_10": 0.21778, + "map_at_100": 0.22747, + "map_at_1000": 0.22891, + "map_at_20": 0.22259, + "map_at_3": 0.20033, + "map_at_5": 0.20978, + "mrr_at_1": 0.312, + "mrr_at_10": 0.38151111111111075, + "mrr_at_100": 0.3898793372817461, + "mrr_at_1000": 0.39056015236079966, + "mrr_at_20": 0.38653504905397257, + "mrr_at_3": 0.36033333333333306, + "mrr_at_5": 0.37223333333333275, + "nauc_map_at_1000_diff1": 0.45881856814323707, + "nauc_map_at_1000_max": 0.3382718710587777, + "nauc_map_at_1000_std": 0.16698962865919065, + "nauc_map_at_100_diff1": 0.45906114206914866, + "nauc_map_at_100_max": 0.3379835146240387, + "nauc_map_at_100_std": 0.1660672248702478, + "nauc_map_at_10_diff1": 0.4675593284038509, + "nauc_map_at_10_max": 0.3365334924073432, + "nauc_map_at_10_std": 0.1548823176814751, + "nauc_map_at_1_diff1": 0.5890700385760184, + "nauc_map_at_1_max": 0.3717360820089617, + "nauc_map_at_1_std": 0.1228871839506572, + "nauc_map_at_20_diff1": 0.46317361534166196, + "nauc_map_at_20_max": 0.3361297401143429, + "nauc_map_at_20_std": 0.16133557833848775, + "nauc_map_at_3_diff1": 0.4956403363787955, + "nauc_map_at_3_max": 0.3331311673178324, + "nauc_map_at_3_std": 0.13666343103140657, + "nauc_map_at_5_diff1": 0.48007247562921135, + "nauc_map_at_5_max": 0.3329798260285387, + "nauc_map_at_5_std": 0.14667132382818546, + "nauc_mrr_at_1000_diff1": 0.5265934186043765, + "nauc_mrr_at_1000_max": 0.36401817168290623, + "nauc_mrr_at_1000_std": 0.14726658550225635, + "nauc_mrr_at_100_diff1": 0.5262449467361637, + "nauc_mrr_at_100_max": 0.3638476782121034, + "nauc_mrr_at_100_std": 0.14706627681997678, + "nauc_mrr_at_10_diff1": 0.527784496856924, + "nauc_mrr_at_10_max": 0.3641574793880368, + "nauc_mrr_at_10_std": 0.1446656107711577, + "nauc_mrr_at_1_diff1": 0.5890700385760184, + "nauc_mrr_at_1_max": 0.3717360820089617, + "nauc_mrr_at_1_std": 0.1228871839506572, + "nauc_mrr_at_20_diff1": 0.5262327138082133, + "nauc_mrr_at_20_max": 0.363520433137821, + "nauc_mrr_at_20_std": 0.14656731885844498, + "nauc_mrr_at_3_diff1": 0.544072750407305, + "nauc_mrr_at_3_max": 0.36041572164143343, + "nauc_mrr_at_3_std": 0.13366708214778933, + "nauc_mrr_at_5_diff1": 0.5324801050630977, + "nauc_mrr_at_5_max": 0.3607241316559795, + "nauc_mrr_at_5_std": 0.14138768485435624, + "nauc_ndcg_at_1000_diff1": 0.41969810851445877, + "nauc_ndcg_at_1000_max": 0.3613914169851042, + "nauc_ndcg_at_1000_std": 0.22216002690796502, + "nauc_ndcg_at_100_diff1": 0.4199321896347073, + "nauc_ndcg_at_100_max": 0.355004799651079, + "nauc_ndcg_at_100_std": 0.20718713737396205, + "nauc_ndcg_at_10_diff1": 0.4529749861198433, + "nauc_ndcg_at_10_max": 0.3483513880812389, + "nauc_ndcg_at_10_std": 0.16938088096853215, + "nauc_ndcg_at_1_diff1": 0.5890700385760184, + "nauc_ndcg_at_1_max": 0.3717360820089617, + "nauc_ndcg_at_1_std": 0.1228871839506572, + "nauc_ndcg_at_20_diff1": 0.44012476086451463, + "nauc_ndcg_at_20_max": 0.34532073033179445, + "nauc_ndcg_at_20_std": 0.18458028439592494, + "nauc_ndcg_at_3_diff1": 0.49868294845093203, + "nauc_ndcg_at_3_max": 0.3399676729837236, + "nauc_ndcg_at_3_std": 0.1385379500111161, + "nauc_ndcg_at_5_diff1": 0.47383554580804504, + "nauc_ndcg_at_5_max": 0.34015094801967916, + "nauc_ndcg_at_5_std": 0.1549777855225569, + "nauc_precision_at_1000_diff1": 0.03668542377106774, + "nauc_precision_at_1000_max": 0.3211015198596768, + "nauc_precision_at_1000_std": 0.43952837160435543, + "nauc_precision_at_100_diff1": 0.13094039133853072, + "nauc_precision_at_100_max": 0.3029037550237718, + "nauc_precision_at_100_std": 0.31449737257937727, + "nauc_precision_at_10_diff1": 0.32279341442404286, + "nauc_precision_at_10_max": 0.3331711906729857, + "nauc_precision_at_10_std": 0.2131756092219765, + "nauc_precision_at_1_diff1": 0.5890700385760184, + "nauc_precision_at_1_max": 0.3717360820089617, + "nauc_precision_at_1_std": 0.1228871839506572, + "nauc_precision_at_20_diff1": 0.26199895834015147, + "nauc_precision_at_20_max": 0.3053288288246164, + "nauc_precision_at_20_std": 0.2516206974258657, + "nauc_precision_at_3_diff1": 0.45025454630676187, + "nauc_precision_at_3_max": 0.3261633549192578, + "nauc_precision_at_3_std": 0.14677611962557904, + "nauc_precision_at_5_diff1": 0.3881911239127243, + "nauc_precision_at_5_max": 0.32143891672242436, + "nauc_precision_at_5_std": 0.18105488192959826, + "nauc_recall_at_1000_diff1": 0.03668542377106788, + "nauc_recall_at_1000_max": 0.3211015198596775, + "nauc_recall_at_1000_std": 0.43952837160435526, + "nauc_recall_at_100_diff1": 0.1309403913385309, + "nauc_recall_at_100_max": 0.30290375502377137, + "nauc_recall_at_100_std": 0.3144973725793775, + "nauc_recall_at_10_diff1": 0.3227934144240429, + "nauc_recall_at_10_max": 0.33317119067298545, + "nauc_recall_at_10_std": 0.21317560922197665, + "nauc_recall_at_1_diff1": 0.5890700385760184, + "nauc_recall_at_1_max": 0.3717360820089617, + "nauc_recall_at_1_std": 0.1228871839506572, + "nauc_recall_at_20_diff1": 0.2619989583401516, + "nauc_recall_at_20_max": 0.3053288288246171, + "nauc_recall_at_20_std": 0.25162069742586635, + "nauc_recall_at_3_diff1": 0.4502545463067617, + "nauc_recall_at_3_max": 0.3261633549192579, + "nauc_recall_at_3_std": 0.14677611962557907, + "nauc_recall_at_5_diff1": 0.388191123912724, + "nauc_recall_at_5_max": 0.32143891672242453, + "nauc_recall_at_5_std": 0.18105488192959815, + "ndcg_at_1": 0.312, + "ndcg_at_10": 0.28296, + "ndcg_at_100": 0.33037, + "ndcg_at_1000": 0.36389, + "ndcg_at_20": 0.29895, + "ndcg_at_3": 0.24693, + "ndcg_at_5": 0.26416, + "precision_at_1": 0.312, + "precision_at_10": 0.0631, + "precision_at_100": 0.01017, + "precision_at_1000": 0.00146, + "precision_at_20": 0.03665, + "precision_at_3": 0.15567, + "precision_at_5": 0.1072, + "recall_at_1": 0.156, + "recall_at_10": 0.3155, + "recall_at_100": 0.5085, + "recall_at_1000": 0.7315, + "recall_at_20": 0.3665, + "recall_at_3": 0.2335, + "recall_at_5": 0.268 + } + ] + }, + "task_name": "HotpotQAHardNegatives" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ImdbClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ImdbClassification.json new file mode 100644 index 000000000..9d69592ef --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/ImdbClassification.json @@ -0,0 +1,95 @@ +{ + "dataset_revision": "3d86128a09e091d6018b6d26cad27f2739fc2db7", + "evaluation_time": 194.23965501785278, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.636532, + "ap": 0.5893182602735416, + "ap_weighted": 0.5893182602735416, + "f1": 0.6352591560926554, + "f1_weighted": 0.6352591560926554, + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.636532, + "scores_per_experiment": [ + { + "accuracy": 0.65344, + "ap": 0.6029778443968594, + "ap_weighted": 0.6029778443968594, + "f1": 0.6525119210550208, + "f1_weighted": 0.6525119210550208 + }, + { + "accuracy": 0.63024, + "ap": 0.5864039510138526, + "ap_weighted": 0.5864039510138526, + "f1": 0.6263894537415469, + "f1_weighted": 0.6263894537415468 + }, + { + "accuracy": 0.59056, + "ap": 0.5552950371238765, + "ap_weighted": 0.5552950371238765, + "f1": 0.5871743701122994, + "f1_weighted": 0.5871743701122996 + }, + { + "accuracy": 0.67584, + "ap": 0.6190940861429264, + "ap_weighted": 0.6190940861429264, + "f1": 0.6758346038131489, + "f1_weighted": 0.6758346038131489 + }, + { + "accuracy": 0.6604, + "ap": 0.6116248583154191, + "ap_weighted": 0.6116248583154191, + "f1": 0.657586867380485, + "f1_weighted": 0.6575868673804851 + }, + { + "accuracy": 0.63488, + "ap": 0.5857734150274105, + "ap_weighted": 0.5857734150274105, + "f1": 0.6348746160071378, + "f1_weighted": 0.6348746160071378 + }, + { + "accuracy": 0.62464, + "ap": 0.5788382987410684, + "ap_weighted": 0.5788382987410684, + "f1": 0.6243072648738708, + "f1_weighted": 0.6243072648738708 + }, + { + "accuracy": 0.65628, + "ap": 0.6007794497589914, + "ap_weighted": 0.6007794497589914, + "f1": 0.6557455932291052, + "f1_weighted": 0.6557455932291052 + }, + { + "accuracy": 0.58972, + "ap": 0.5532555761368377, + "ap_weighted": 0.5532555761368377, + "f1": 0.5895458196640326, + "f1_weighted": 0.5895458196640326 + }, + { + "accuracy": 0.64932, + "ap": 0.599140086078173, + "ap_weighted": 0.599140086078173, + "f1": 0.6486210510499064, + "f1_weighted": 0.6486210510499064 + } + ] + } + ] + }, + "task_name": "ImdbClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MTOPDomainClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MTOPDomainClassification.json new file mode 100644 index 000000000..c027eb95e --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MTOPDomainClassification.json @@ -0,0 +1,73 @@ +{ + "dataset_revision": "d80d48c1eb48d3562165c59d59d0034df9fff0bf", + "evaluation_time": 9.597903490066528, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.8245326037391703, + "f1": 0.8160911959596427, + "f1_weighted": 0.8255011639256074, + "hf_subset": "en", + "languages": [ + "eng-Latn" + ], + "main_score": 0.8245326037391703, + "scores_per_experiment": [ + { + "accuracy": 0.7922936616507068, + "f1": 0.7834343353771979, + "f1_weighted": 0.7919387398656655 + }, + { + "accuracy": 0.8331053351573188, + "f1": 0.8218458890845483, + "f1_weighted": 0.832819478176042 + }, + { + "accuracy": 0.8333333333333334, + "f1": 0.8249683352220102, + "f1_weighted": 0.8331669959907568 + }, + { + "accuracy": 0.8321933424532604, + "f1": 0.822249028333388, + "f1_weighted": 0.8358219517542419 + }, + { + "accuracy": 0.8280893752849977, + "f1": 0.8218145974587323, + "f1_weighted": 0.8277379661447974 + }, + { + "accuracy": 0.8392612859097127, + "f1": 0.832180872913473, + "f1_weighted": 0.8415090145626829 + }, + { + "accuracy": 0.823985408116735, + "f1": 0.8145407905020586, + "f1_weighted": 0.8250529308909134 + }, + { + "accuracy": 0.8160054719562243, + "f1": 0.8063962765201708, + "f1_weighted": 0.8176080377998799 + }, + { + "accuracy": 0.8182854537163703, + "f1": 0.8141195987995641, + "f1_weighted": 0.8199538318479838 + }, + { + "accuracy": 0.8287733698130415, + "f1": 0.8193622353852846, + "f1_weighted": 0.8294026922231104 + } + ] + } + ] + }, + "task_name": "MTOPDomainClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveIntentClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveIntentClassification.json new file mode 100644 index 000000000..8cd3ca00e --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveIntentClassification.json @@ -0,0 +1,73 @@ +{ + "dataset_revision": "4672e20407010da34463acc759c162ca9734bca6", + "evaluation_time": 14.903557538986206, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.5805648957632819, + "f1": 0.5532287486692983, + "f1_weighted": 0.5864168224827864, + "hf_subset": "en", + "languages": [ + "eng-Latn" + ], + "main_score": 0.5805648957632819, + "scores_per_experiment": [ + { + "accuracy": 0.5655682582380632, + "f1": 0.5429373376717267, + "f1_weighted": 0.5661112806282773 + }, + { + "accuracy": 0.6230665770006725, + "f1": 0.576019505034855, + "f1_weighted": 0.6296608594893245 + }, + { + "accuracy": 0.5901143241425689, + "f1": 0.5544806485047343, + "f1_weighted": 0.5893764113774913 + }, + { + "accuracy": 0.5877605917955615, + "f1": 0.5605497559576917, + "f1_weighted": 0.5919395008918547 + }, + { + "accuracy": 0.5928043039677202, + "f1": 0.5588891396982257, + "f1_weighted": 0.5993485579841895 + }, + { + "accuracy": 0.5568258238063215, + "f1": 0.541963336447261, + "f1_weighted": 0.5684905451767049 + }, + { + "accuracy": 0.5605245460659045, + "f1": 0.5429277831687386, + "f1_weighted": 0.5688489338952086 + }, + { + "accuracy": 0.5776731674512441, + "f1": 0.5476113740330288, + "f1_weighted": 0.5876830731771711 + }, + { + "accuracy": 0.5682582380632145, + "f1": 0.5449531237959778, + "f1_weighted": 0.5748494531232051 + }, + { + "accuracy": 0.5830531271015468, + "f1": 0.5619554823807431, + "f1_weighted": 0.587859609084437 + } + ] + } + ] + }, + "task_name": "MassiveIntentClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveScenarioClassification.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveScenarioClassification.json new file mode 100644 index 000000000..243a8e615 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MassiveScenarioClassification.json @@ -0,0 +1,73 @@ +{ + "dataset_revision": "fad2c6e8459f9e1c45d9315f4953d921437d70f8", + "evaluation_time": 7.030602216720581, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "accuracy": 0.6209482178883658, + "f1": 0.6102252529995628, + "f1_weighted": 0.6246732771107449, + "hf_subset": "en", + "languages": [ + "eng-Latn" + ], + "main_score": 0.6209482178883658, + "scores_per_experiment": [ + { + "accuracy": 0.636516476126429, + "f1": 0.635245011497225, + "f1_weighted": 0.6450725632437699 + }, + { + "accuracy": 0.6264290517821116, + "f1": 0.6059173564241892, + "f1_weighted": 0.6275267324344401 + }, + { + "accuracy": 0.5988567585743106, + "f1": 0.5942181457588572, + "f1_weighted": 0.6062548279888503 + }, + { + "accuracy": 0.6274377942165433, + "f1": 0.6121188561258362, + "f1_weighted": 0.6289809250782019 + }, + { + "accuracy": 0.6136516476126429, + "f1": 0.5996156375832601, + "f1_weighted": 0.6182651251970076 + }, + { + "accuracy": 0.6220578345662408, + "f1": 0.6056595115016037, + "f1_weighted": 0.6252619648344343 + }, + { + "accuracy": 0.6244115669132482, + "f1": 0.6125623636247312, + "f1_weighted": 0.628635282800664 + }, + { + "accuracy": 0.6237390719569603, + "f1": 0.6127218724018348, + "f1_weighted": 0.6298660932511163 + }, + { + "accuracy": 0.6173503698722259, + "f1": 0.6140623309860398, + "f1_weighted": 0.6195107725294063 + }, + { + "accuracy": 0.6190316072629455, + "f1": 0.6101314440920501, + "f1_weighted": 0.6173584837495592 + } + ] + } + ] + }, + "task_name": "MassiveScenarioClassification" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringP2P.v2.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringP2P.v2.json new file mode 100644 index 000000000..17117d307 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringP2P.v2.json @@ -0,0 +1,34 @@ +{ + "dataset_revision": "e7a26af6f3ae46b30dde8737f02c07b1505bcc73", + "evaluation_time": 23.670560836791992, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.34174611832860946, + "v_measure": 0.34174611832860946, + "v_measure_std": 0.008882226210488849, + "v_measures": { + "Level 0": [ + 0.34159339753315243, + 0.33095191227916576, + 0.32672981178418836, + 0.3341673328114192, + 0.3504333098923567, + 0.3474453797327749, + 0.3453880612562039, + 0.3426699322435061, + 0.35801254564390433, + 0.3400695001094231 + ] + } + } + ] + }, + "task_name": "MedrxivClusteringP2P.v2" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringS2S.v2.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringS2S.v2.json new file mode 100644 index 000000000..3c6e2c362 --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/MedrxivClusteringS2S.v2.json @@ -0,0 +1,34 @@ +{ + "dataset_revision": "35191c8c0dca72d8ff3efcd72aa802307d469663", + "evaluation_time": 5.557464599609375, + "kg_co2_emissions": null, + "mteb_version": "1.19.2", + "scores": { + "test": [ + { + "hf_subset": "default", + "languages": [ + "eng-Latn" + ], + "main_score": 0.2948057125585178, + "v_measure": 0.2948057125585178, + "v_measure_std": 0.008701827284988946, + "v_measures": { + "Level 0": [ + 0.3080113506562818, + 0.28768769941310623, + 0.28416228727731, + 0.30212069165840244, + 0.30628322588242085, + 0.29866980617643646, + 0.29216885441193197, + 0.28787261739784464, + 0.2985183493630435, + 0.2825622433483995 + ] + } + } + ] + }, + "task_name": "MedrxivClusteringS2S.v2" +} \ No newline at end of file diff --git a/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/model_meta.json b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/model_meta.json new file mode 100644 index 000000000..266c7468f --- /dev/null +++ b/results/keeeeenw__MicroLlama-text-embedding/98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e/model_meta.json @@ -0,0 +1 @@ +{"name": "keeeeenw/MicroLlama-text-embedding", "revision": "98f70f14cdf12d7ea217ed2fd4e808b0195f1e7e", "release_date": "2024-11-10", "languages": ["eng-Latn"], "n_parameters": 272000000, "memory_usage": null, "max_tokens": 2048, "embed_dim": 1024, "license": "apache-2.0", "open_weights": true, "public_training_data": null, "public_training_code": null, "framework": ["Sentence Transformers", "PyTorch"], "reference": "https://huggingface.co/keeeeenw/MicroLlama-text-embedding", "similarity_fn_name": "cosine", "use_instructions": false, "zero_shot_benchmarks": null, "loader": null} \ No newline at end of file