Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update results for Russian models #19

Merged
merged 5 commits into from
Sep 6, 2024
Merged

Update results for Russian models #19

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1da91a5
add miracl results
artemsnegirev Aug 15, 2024
2ca9dc3
Merge branch 'main' into add-results-for-rumteb
artemsnegirev Sep 2, 2024
6dd92c4
update results to v1.14.12
artemsnegirev Sep 2, 2024
c5c732b
update cedr and georeview
artemsnegirev Sep 3, 2024
0d2acf4
update clustering
artemsnegirev Sep 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 28 additions & 8 deletions paths.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -360,7 +360,10 @@
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/PublicHealthQA.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/TERRa.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/KinopoiskClassification.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/XNLI.json"
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/XNLI.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/MIRACLReranking.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/MIRACLRetrieval.json",
"results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/STS22.json"
],
"gtr-t5-large": [
"results/gtr-t5-large/no_revision_available/MedrxivClusteringP2P.json",
Expand Down Expand Up @@ -1423,6 +1426,8 @@
"results/intfloat__multilingual-e5-small/e4ce9877abf3edfe10b0d82785e83bdcb973e22e/XNLI.json",
"results/intfloat__multilingual-e5-small/e4ce9877abf3edfe10b0d82785e83bdcb973e22e/InsurancePolicyInterpretationLegalBenchClassification.json",
"results/intfloat__multilingual-e5-small/e4ce9877abf3edfe10b0d82785e83bdcb973e22e/SentimentAnalysisHindi.json",
"results/intfloat__multilingual-e5-small/e4ce9877abf3edfe10b0d82785e83bdcb973e22e/MIRACLReranking.json",
"results/intfloat__multilingual-e5-small/e4ce9877abf3edfe10b0d82785e83bdcb973e22e/MIRACLRetrieval.json",
"results/intfloat__multilingual-e5-small/0a68dcd3dad5b4962a78daa930087728292b241d/NusaParagraphEmotionClassification.json",
"results/intfloat__multilingual-e5-small/0a68dcd3dad5b4962a78daa930087728292b241d/NusaXBitextMining.json",
"results/intfloat__multilingual-e5-small/0a68dcd3dad5b4962a78daa930087728292b241d/CEDRClassification.json",
Expand Down Expand Up @@ -4368,7 +4373,9 @@
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/ContractNLIPermissibleCopyLegalBenchClassification.json",
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/XNLI.json",
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/InsurancePolicyInterpretationLegalBenchClassification.json",
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/SentimentAnalysisHindi.json"
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/SentimentAnalysisHindi.json",
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/MIRACLReranking.json",
"results/intfloat__multilingual-e5-large/4dc6d853a804b9c8886ede6dda8a073b7dc08a81/MIRACLRetrieval.json"
],
"sgpt-bloom-1b7-nli": [
"results/sgpt-bloom-1b7-nli/no_revision_available/AmazonReviewsClassification.json",
Expand Down Expand Up @@ -9645,7 +9652,9 @@
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/ContractNLIPermissibleCopyLegalBenchClassification.json",
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/XNLI.json",
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/InsurancePolicyInterpretationLegalBenchClassification.json",
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/SentimentAnalysisHindi.json"
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/SentimentAnalysisHindi.json",
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/MIRACLReranking.json",
"results/intfloat__multilingual-e5-large-instruct/baa7be480a7de1539afce709c8f13f833a510e0a/MIRACLRetrieval.json"
],
"glove.6B.300d": [
"results/glove.6B.300d/no_revision_available/MedrxivClusteringP2P.json",
Expand Down Expand Up @@ -9740,7 +9749,9 @@
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/GeoreviewClassification.json",
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/TERRa.json",
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/KinopoiskClassification.json",
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/XNLI.json"
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/XNLI.json",
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/MIRACLReranking.json",
"results/ai-forever__sbert_large_nlu_ru/af977d5dfa46a3635e29bf0ef383f2df2a08d47a/MIRACLRetrieval.json"
],
"OpenSearch-text-hybrid": [
"results/OpenSearch-text-hybrid/no_revision_available/ThuNewsClusteringP2P.json",
Expand Down Expand Up @@ -12000,7 +12011,9 @@
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/ContractNLIPermissibleCopyLegalBenchClassification.json",
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/XNLI.json",
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/InsurancePolicyInterpretationLegalBenchClassification.json",
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/SentimentAnalysisHindi.json"
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/SentimentAnalysisHindi.json",
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/MIRACLReranking.json",
"results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040960d60d909913633f/MIRACLRetrieval.json"
],
"intfloat__e5-base-v2": [
"results/intfloat__e5-base-v2/1c644c92ad3ba1efdad3f1451a637716616a20e8/TwentyNewsgroupsClustering.v2.json",
Expand Down Expand Up @@ -13304,7 +13317,9 @@
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/GeoreviewClassification.json",
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/TERRa.json",
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/KinopoiskClassification.json",
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/XNLI.json"
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/XNLI.json",
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/MIRACLReranking.json",
"results/ai-forever__sbert_large_mt_nlu_ru/05300876c2b83f46d3ddd422a7f17e45cf633bb0/MIRACLRetrieval.json"
],
"Cohere-embed-english-v3.0": [
"results/Cohere-embed-english-v3.0/no_revision_available/GerDaLIRSmall.json",
Expand Down Expand Up @@ -15376,7 +15391,10 @@
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/ContractNLIPermissibleCopyLegalBenchClassification.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/XNLI.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/InsurancePolicyInterpretationLegalBenchClassification.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SentimentAnalysisHindi.json"
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/SentimentAnalysisHindi.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/MIRACLReranking.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/MIRACLRetrieval.json",
"results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360786df853f237b1a3ca1/STS22.json"
],
"cointegrated__rubert-tiny2": [
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/GeoreviewClusteringP2P.json",
Expand All @@ -15400,7 +15418,9 @@
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/GeoreviewClassification.json",
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/TERRa.json",
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/KinopoiskClassification.json",
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/XNLI.json"
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/XNLI.json",
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/MIRACLReranking.json",
"results/cointegrated__rubert-tiny2/dad72b8f77c5eef6995dd3e4691b758ba56b90c3/MIRACLRetrieval.json"
],
"allenai-specter": [
"results/allenai-specter/no_revision_available/MedrxivClusteringP2P.json",
Expand Down
2 changes: 1 addition & 1 deletion results.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@
# Use "validation" split instead
VALIDATION_SPLIT = ["AFQMC", "Cmnli", "IFlyTek", "LEMBSummScreenFDRetrieval", "MSMARCO", "MSMARCO-PL", "MultilingualSentiment", "Ocnli", "TNews"]
# Use "dev" split instead
DEV_SPLIT = ["CmedqaRetrieval", "CovidRetrieval", "DuRetrieval", "EcomRetrieval", "MedicalRetrieval", "MMarcoReranking", "MMarcoRetrieval", "MSMARCO", "MSMARCO-PL", "T2Reranking", "T2Retrieval", "VideoRetrieval", "TERRa",]
DEV_SPLIT = ["CmedqaRetrieval", "CovidRetrieval", "DuRetrieval", "EcomRetrieval", "MedicalRetrieval", "MMarcoReranking", "MMarcoRetrieval", "MSMARCO", "MSMARCO-PL", "T2Reranking", "T2Retrieval", "VideoRetrieval", "TERRa", "MIRACLReranking", "MIRACLRetrieval"]
# Use "test.full" split
TESTFULL_SPLIT = ["OpusparcusPC"]
# Use "standard" split
Expand Down
6 changes: 3 additions & 3 deletions results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/CEDRClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
{
"dataset_revision": "c0ba03d058e3e1b2f3fd20518875a4563dd12db4",
"evaluation_time": 9.198393106460571,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 6.249963283538818,
"kg_co2_emissions": 0.001172516433590914,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
Expand Down
74 changes: 37 additions & 37 deletions results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/GeoreviewClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,69 +1,69 @@
{
"dataset_revision": "3765c0d1de6b7d264bc459433c45e5a75513839c",
"evaluation_time": 75.7588369846344,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 29.75946879386902,
"kg_co2_emissions": 0.00562288263049014,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
"accuracy": 0.48271484375,
"f1": 0.4637639894318407,
"f1_weighted": 0.4637502353335761,
"accuracy": 0.490234375,
"f1": 0.45975728150225026,
"f1_weighted": 0.45973414696445947,
"hf_subset": "default",
"languages": [
"rus-Cyrl"
],
"main_score": 0.48271484375,
"main_score": 0.490234375,
"scores_per_experiment": [
{
"accuracy": 0.49072265625,
"f1": 0.46486358408529094,
"f1_weighted": 0.46484173042355137
"accuracy": 0.49462890625,
"f1": 0.4809297834552235,
"f1_weighted": 0.4809279189463784
},
{
"accuracy": 0.48876953125,
"f1": 0.46959441816866415,
"f1_weighted": 0.46956089548416896
"accuracy": 0.49169921875,
"f1": 0.44616355612448,
"f1_weighted": 0.4461250769379079
},
{
"accuracy": 0.48193359375,
"f1": 0.4509998045582305,
"f1_weighted": 0.45099352983410884
"accuracy": 0.49658203125,
"f1": 0.4456497312678735,
"f1_weighted": 0.4455590589830963
},
{
"accuracy": 0.47802734375,
"f1": 0.4548544171701458,
"f1_weighted": 0.45488756868959157
"accuracy": 0.49755859375,
"f1": 0.4773686533722629,
"f1_weighted": 0.4773272657378211
},
{
"accuracy": 0.5029296875,
"f1": 0.4847142481823127,
"f1_weighted": 0.48468811544616464
"accuracy": 0.46435546875,
"f1": 0.43250389380112536,
"f1_weighted": 0.4325113772752217
},
{
"accuracy": 0.447265625,
"f1": 0.43312926318029854,
"f1_weighted": 0.43312621602728213
"accuracy": 0.51025390625,
"f1": 0.4891932597261063,
"f1_weighted": 0.489160536915776
},
{
"accuracy": 0.49658203125,
"f1": 0.47889490845335736,
"f1_weighted": 0.47887504447157925
"accuracy": 0.4951171875,
"f1": 0.4697964954606505,
"f1_weighted": 0.46980964666569397
},
{
"accuracy": 0.48974609375,
"f1": 0.4820021759101446,
"f1_weighted": 0.4819651386483531
"accuracy": 0.49462890625,
"f1": 0.46912257318478207,
"f1_weighted": 0.4691040704344313
},
{
"accuracy": 0.4560546875,
"f1": 0.45658160299568423,
"f1_weighted": 0.4565737309001588
"accuracy": 0.48681640625,
"f1": 0.46835102334684214,
"f1_weighted": 0.46835744981626815
},
{
"accuracy": 0.4951171875,
"f1": 0.4620054716142782,
"f1_weighted": 0.46199038341080273
"accuracy": 0.470703125,
"f1": 0.4184938452831564,
"f1_weighted": 0.41845906793199994
}
]
}
Expand Down
32 changes: 16 additions & 16 deletions results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/GeoreviewClusteringP2P.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,30 +1,30 @@
{
"dataset_revision": "97a313c8fc85b47f13f33e7e9a95c1ad888c7fec",
"evaluation_time": 27.409440279006958,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 18.1637966632843,
"kg_co2_emissions": 0.003436204840852146,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
"hf_subset": "default",
"languages": [
"rus-Cyrl"
],
"main_score": 0.6374589062121784,
"v_measure": 0.6374589062121784,
"v_measure_std": 0.009208765511913278,
"main_score": 0.6309362350401001,
"v_measure": 0.6309362350401001,
"v_measure_std": 0.0069216250600025765,
"v_measures": {
"Level 0": [
0.6370327148594535,
0.6424596073999332,
0.6392741465582813,
0.6329263277865536,
0.6590701918285066,
0.622271661496703,
0.6426101042028406,
0.6313427549279668,
0.6361007293081735,
0.6315008237533719
0.6267491457669475,
0.6394904887571816,
0.6217508612620499,
0.6431213086665305,
0.637728409663516,
0.6322784611556416,
0.6253432498893571,
0.6222903585974335,
0.6296844891597609,
0.6309255774825824
]
}
}
Expand Down
6 changes: 3 additions & 3 deletions results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/HeadlineClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
{
"dataset_revision": "2fe05ee6b5832cda29f2ef7aaad7b7fe6a3609eb",
"evaluation_time": 6.287163972854614,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 11.900310754776001,
"kg_co2_emissions": 0.002089357523881271,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
Expand Down
6 changes: 3 additions & 3 deletions ...AAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/InappropriatenessClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
{
"dataset_revision": "601651fdc45ef243751676e62dd7a19f491c0285",
"evaluation_time": 14.860052824020386,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 13.090336322784424,
"kg_co2_emissions": 0.00233230834855967,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
Expand Down
6 changes: 3 additions & 3 deletions results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/KinopoiskClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
{
"dataset_revision": "5911f26666ac11af46cb9c6849d0dc80a378af24",
"evaluation_time": 114.3788833618164,
"kg_co2_emissions": null,
"mteb_version": "1.12.89",
"evaluation_time": 58.81527352333069,
"kg_co2_emissions": 0.011789179964316132,
"mteb_version": "1.14.12",
"scores": {
"test": [
{
Expand Down
Loading
Loading