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

feat: evaluate openai models on the remaining MTEB(Medical) tasks #71

Merged
merged 1 commit into from
Dec 14, 2024
Merged

feat: evaluate openai models on the remaining MTEB(Medical) tasks #71

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
26 changes: 26 additions & 0 deletions results/openai__text-embedding-3-large/2/CMedQAv2-reranking.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
{
"dataset_revision": "23d186750531a14a0357ca22cd92d712fd512ea0",
"task_name": "CMedQAv2-reranking",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"map": 0.751224,
"mrr": 0.788045,
"nAUC_map_max": 0.532528,
"nAUC_map_std": 0.170824,
"nAUC_map_diff1": 0.506192,
"nAUC_mrr_max": 0.619113,
"nAUC_mrr_std": 0.232415,
"nAUC_mrr_diff1": 0.582075,
"main_score": 0.751224,
"hf_subset": "default",
"languages": [
"cmn-Hans"
]
}
]
},
"evaluation_time": 1884.4257838726044,
"kg_co2_emissions": 0.00044117606664305007
}
158 changes: 158 additions & 0 deletions results/openai__text-embedding-3-large/2/CmedqaRetrieval.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "cd540c506dae1cf9e9a59c3e06f42030d54e7301",
"task_name": "CmedqaRetrieval",
"mteb_version": "1.24.0",
"scores": {
"dev": [
{
"ndcg_at_1": 0.23806,
"ndcg_at_3": 0.24019,
"ndcg_at_5": 0.25216,
"ndcg_at_10": 0.27435,
"ndcg_at_20": 0.29721,
"ndcg_at_100": 0.34303,
"ndcg_at_1000": 0.38144,
"map_at_1": 0.14967,
"map_at_3": 0.20044,
"map_at_5": 0.21298,
"map_at_10": 0.22494,
"map_at_20": 0.2325,
"map_at_100": 0.2402,
"map_at_1000": 0.24198,
"recall_at_1": 0.14967,
"recall_at_3": 0.24011,
"recall_at_5": 0.28091,
"recall_at_10": 0.34567,
"recall_at_20": 0.42386,
"recall_at_100": 0.63685,
"recall_at_1000": 0.90421,
"precision_at_1": 0.23806,
"precision_at_3": 0.1382,
"precision_at_5": 0.09947,
"precision_at_10": 0.06294,
"precision_at_20": 0.039,
"precision_at_100": 0.01199,
"precision_at_1000": 0.0017,
"mrr_at_1": 0.23806,
"mrr_at_3": 0.281279,
"mrr_at_5": 0.291931,
"mrr_at_10": 0.301517,
"mrr_at_20": 0.306952,
"mrr_at_100": 0.311724,
"mrr_at_1000": 0.312605,
"nauc_ndcg_at_1_max": 0.385752,
"nauc_ndcg_at_1_std": -0.040464,
"nauc_ndcg_at_1_diff1": 0.52806,
"nauc_ndcg_at_3_max": 0.34744,
"nauc_ndcg_at_3_std": -0.040927,
"nauc_ndcg_at_3_diff1": 0.446717,
"nauc_ndcg_at_5_max": 0.338609,
"nauc_ndcg_at_5_std": -0.045501,
"nauc_ndcg_at_5_diff1": 0.438516,
"nauc_ndcg_at_10_max": 0.339566,
"nauc_ndcg_at_10_std": -0.043432,
"nauc_ndcg_at_10_diff1": 0.429259,
"nauc_ndcg_at_20_max": 0.343991,
"nauc_ndcg_at_20_std": -0.026292,
"nauc_ndcg_at_20_diff1": 0.421478,
"nauc_ndcg_at_100_max": 0.347669,
"nauc_ndcg_at_100_std": 0.000656,
"nauc_ndcg_at_100_diff1": 0.412529,
"nauc_ndcg_at_1000_max": 0.356152,
"nauc_ndcg_at_1000_std": 0.004637,
"nauc_ndcg_at_1000_diff1": 0.422442,
"nauc_map_at_1_max": 0.301477,
"nauc_map_at_1_std": -0.072747,
"nauc_map_at_1_diff1": 0.493146,
"nauc_map_at_3_max": 0.326267,
"nauc_map_at_3_std": -0.060284,
"nauc_map_at_3_diff1": 0.454711,
"nauc_map_at_5_max": 0.330391,
"nauc_map_at_5_std": -0.058726,
"nauc_map_at_5_diff1": 0.449565,
"nauc_map_at_10_max": 0.336287,
"nauc_map_at_10_std": -0.055241,
"nauc_map_at_10_diff1": 0.443792,
"nauc_map_at_20_max": 0.339646,
"nauc_map_at_20_std": -0.049295,
"nauc_map_at_20_diff1": 0.441548,
"nauc_map_at_100_max": 0.341537,
"nauc_map_at_100_std": -0.043372,
"nauc_map_at_100_diff1": 0.440142,
"nauc_map_at_1000_max": 0.342049,
"nauc_map_at_1000_std": -0.042582,
"nauc_map_at_1000_diff1": 0.440503,
"nauc_recall_at_1_max": 0.301477,
"nauc_recall_at_1_std": -0.072747,
"nauc_recall_at_1_diff1": 0.493146,
"nauc_recall_at_3_max": 0.291041,
"nauc_recall_at_3_std": -0.053511,
"nauc_recall_at_3_diff1": 0.393961,
"nauc_recall_at_5_max": 0.283306,
"nauc_recall_at_5_std": -0.048442,
"nauc_recall_at_5_diff1": 0.364103,
"nauc_recall_at_10_max": 0.284127,
"nauc_recall_at_10_std": -0.03875,
"nauc_recall_at_10_diff1": 0.334214,
"nauc_recall_at_20_max": 0.290039,
"nauc_recall_at_20_std": 0.015398,
"nauc_recall_at_20_diff1": 0.30011,
"nauc_recall_at_100_max": 0.286998,
"nauc_recall_at_100_std": 0.132302,
"nauc_recall_at_100_diff1": 0.233188,
"nauc_recall_at_1000_max": 0.416109,
"nauc_recall_at_1000_std": 0.408188,
"nauc_recall_at_1000_diff1": 0.204341,
"nauc_precision_at_1_max": 0.385752,
"nauc_precision_at_1_std": -0.040464,
"nauc_precision_at_1_diff1": 0.52806,
"nauc_precision_at_3_max": 0.386608,
"nauc_precision_at_3_std": -0.00421,
"nauc_precision_at_3_diff1": 0.386592,
"nauc_precision_at_5_max": 0.370232,
"nauc_precision_at_5_std": 0.001644,
"nauc_precision_at_5_diff1": 0.350039,
"nauc_precision_at_10_max": 0.366455,
"nauc_precision_at_10_std": 0.029112,
"nauc_precision_at_10_diff1": 0.297162,
"nauc_precision_at_20_max": 0.350007,
"nauc_precision_at_20_std": 0.070674,
"nauc_precision_at_20_diff1": 0.254044,
"nauc_precision_at_100_max": 0.27252,
"nauc_precision_at_100_std": 0.160222,
"nauc_precision_at_100_diff1": 0.148347,
"nauc_precision_at_1000_max": 0.198375,
"nauc_precision_at_1000_std": 0.16985,
"nauc_precision_at_1000_diff1": 0.065617,
"nauc_mrr_at_1_max": 0.385752,
"nauc_mrr_at_1_std": -0.040464,
"nauc_mrr_at_1_diff1": 0.52806,
"nauc_mrr_at_3_max": 0.366945,
"nauc_mrr_at_3_std": -0.029993,
"nauc_mrr_at_3_diff1": 0.484221,
"nauc_mrr_at_5_max": 0.365061,
"nauc_mrr_at_5_std": -0.028935,
"nauc_mrr_at_5_diff1": 0.478225,
"nauc_mrr_at_10_max": 0.364478,
"nauc_mrr_at_10_std": -0.027304,
"nauc_mrr_at_10_diff1": 0.473609,
"nauc_mrr_at_20_max": 0.364233,
"nauc_mrr_at_20_std": -0.023302,
"nauc_mrr_at_20_diff1": 0.471052,
"nauc_mrr_at_100_max": 0.364592,
"nauc_mrr_at_100_std": -0.021667,
"nauc_mrr_at_100_diff1": 0.470421,
"nauc_mrr_at_1000_max": 0.364768,
"nauc_mrr_at_1000_std": -0.021747,
"nauc_mrr_at_1000_diff1": 0.470786,
"main_score": 0.27435,
"hf_subset": "default",
"languages": [
"cmn-Hans"
]
}
]
},
"evaluation_time": 2936.1834087371826,
"kg_co2_emissions": 0.0005700112053268032
}
158 changes: 158 additions & 0 deletions results/openai__text-embedding-3-large/2/MedicalQARetrieval.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "ae763399273d8b20506b80cf6f6f9a31a6a2b238",
"task_name": "MedicalQARetrieval",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"ndcg_at_1": 0.66406,
"ndcg_at_3": 0.76001,
"ndcg_at_5": 0.78057,
"ndcg_at_10": 0.79657,
"ndcg_at_20": 0.804,
"ndcg_at_100": 0.80889,
"ndcg_at_1000": 0.81129,
"map_at_1": 0.66406,
"map_at_3": 0.73706,
"map_at_5": 0.74861,
"map_at_10": 0.75525,
"map_at_20": 0.75736,
"map_at_100": 0.75807,
"map_at_1000": 0.75816,
"recall_at_1": 0.66406,
"recall_at_3": 0.82617,
"recall_at_5": 0.87549,
"recall_at_10": 0.9248,
"recall_at_20": 0.95361,
"recall_at_100": 0.97949,
"recall_at_1000": 0.99854,
"precision_at_1": 0.66406,
"precision_at_3": 0.27539,
"precision_at_5": 0.1751,
"precision_at_10": 0.09248,
"precision_at_20": 0.04768,
"precision_at_100": 0.00979,
"precision_at_1000": 0.001,
"mrr_at_1": 0.664062,
"mrr_at_3": 0.736735,
"mrr_at_5": 0.748161,
"mrr_at_10": 0.754961,
"mrr_at_20": 0.757079,
"mrr_at_100": 0.757784,
"mrr_at_1000": 0.757873,
"nauc_ndcg_at_1_max": 0.433356,
"nauc_ndcg_at_1_std": -0.091583,
"nauc_ndcg_at_1_diff1": 0.694226,
"nauc_ndcg_at_3_max": 0.420168,
"nauc_ndcg_at_3_std": -0.131054,
"nauc_ndcg_at_3_diff1": 0.646435,
"nauc_ndcg_at_5_max": 0.41975,
"nauc_ndcg_at_5_std": -0.139749,
"nauc_ndcg_at_5_diff1": 0.645507,
"nauc_ndcg_at_10_max": 0.428545,
"nauc_ndcg_at_10_std": -0.150018,
"nauc_ndcg_at_10_diff1": 0.644121,
"nauc_ndcg_at_20_max": 0.427207,
"nauc_ndcg_at_20_std": -0.126902,
"nauc_ndcg_at_20_diff1": 0.646615,
"nauc_ndcg_at_100_max": 0.427837,
"nauc_ndcg_at_100_std": -0.117718,
"nauc_ndcg_at_100_diff1": 0.652459,
"nauc_ndcg_at_1000_max": 0.425608,
"nauc_ndcg_at_1000_std": -0.121263,
"nauc_ndcg_at_1000_diff1": 0.654148,
"nauc_map_at_1_max": 0.433356,
"nauc_map_at_1_std": -0.091583,
"nauc_map_at_1_diff1": 0.694226,
"nauc_map_at_3_max": 0.421986,
"nauc_map_at_3_std": -0.119741,
"nauc_map_at_3_diff1": 0.659279,
"nauc_map_at_5_max": 0.421911,
"nauc_map_at_5_std": -0.123421,
"nauc_map_at_5_diff1": 0.659557,
"nauc_map_at_10_max": 0.424924,
"nauc_map_at_10_std": -0.126781,
"nauc_map_at_10_diff1": 0.659324,
"nauc_map_at_20_max": 0.424638,
"nauc_map_at_20_std": -0.121343,
"nauc_map_at_20_diff1": 0.660062,
"nauc_map_at_100_max": 0.424713,
"nauc_map_at_100_std": -0.119872,
"nauc_map_at_100_diff1": 0.660823,
"nauc_map_at_1000_max": 0.424617,
"nauc_map_at_1000_std": -0.119899,
"nauc_map_at_1000_diff1": 0.660859,
"nauc_recall_at_1_max": 0.433356,
"nauc_recall_at_1_std": -0.091583,
"nauc_recall_at_1_diff1": 0.694226,
"nauc_recall_at_3_max": 0.414072,
"nauc_recall_at_3_std": -0.176215,
"nauc_recall_at_3_diff1": 0.595665,
"nauc_recall_at_5_max": 0.409939,
"nauc_recall_at_5_std": -0.226551,
"nauc_recall_at_5_diff1": 0.573048,
"nauc_recall_at_10_max": 0.470337,
"nauc_recall_at_10_std": -0.351935,
"nauc_recall_at_10_diff1": 0.520716,
"nauc_recall_at_20_max": 0.475081,
"nauc_recall_at_20_std": -0.14001,
"nauc_recall_at_20_diff1": 0.479932,
"nauc_recall_at_100_max": 0.561001,
"nauc_recall_at_100_std": 0.183469,
"nauc_recall_at_100_diff1": 0.513431,
"nauc_recall_at_1000_max": 0.565963,
"nauc_recall_at_1000_std": 0.391581,
"nauc_recall_at_1000_diff1": 0.322598,
"nauc_precision_at_1_max": 0.433356,
"nauc_precision_at_1_std": -0.091583,
"nauc_precision_at_1_diff1": 0.694226,
"nauc_precision_at_3_max": 0.414072,
"nauc_precision_at_3_std": -0.176215,
"nauc_precision_at_3_diff1": 0.595665,
"nauc_precision_at_5_max": 0.409939,
"nauc_precision_at_5_std": -0.226551,
"nauc_precision_at_5_diff1": 0.573048,
"nauc_precision_at_10_max": 0.470337,
"nauc_precision_at_10_std": -0.351935,
"nauc_precision_at_10_diff1": 0.520716,
"nauc_precision_at_20_max": 0.475081,
"nauc_precision_at_20_std": -0.14001,
"nauc_precision_at_20_diff1": 0.479932,
"nauc_precision_at_100_max": 0.561001,
"nauc_precision_at_100_std": 0.183469,
"nauc_precision_at_100_diff1": 0.513431,
"nauc_precision_at_1000_max": 0.565963,
"nauc_precision_at_1000_std": 0.391581,
"nauc_precision_at_1000_diff1": 0.322598,
"nauc_mrr_at_1_max": 0.434137,
"nauc_mrr_at_1_std": -0.08679,
"nauc_mrr_at_1_diff1": 0.694226,
"nauc_mrr_at_3_max": 0.422952,
"nauc_mrr_at_3_std": -0.115251,
"nauc_mrr_at_3_diff1": 0.659957,
"nauc_mrr_at_5_max": 0.423275,
"nauc_mrr_at_5_std": -0.118462,
"nauc_mrr_at_5_diff1": 0.660504,
"nauc_mrr_at_10_max": 0.426052,
"nauc_mrr_at_10_std": -0.122276,
"nauc_mrr_at_10_diff1": 0.659972,
"nauc_mrr_at_20_max": 0.425811,
"nauc_mrr_at_20_std": -0.116797,
"nauc_mrr_at_20_diff1": 0.660715,
"nauc_mrr_at_100_max": 0.425891,
"nauc_mrr_at_100_std": -0.115313,
"nauc_mrr_at_100_diff1": 0.661478,
"nauc_mrr_at_1000_max": 0.425795,
"nauc_mrr_at_1000_std": -0.115338,
"nauc_mrr_at_1000_diff1": 0.661514,
"main_score": 0.79657,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 81.16353392601013,
"kg_co2_emissions": 2.6804755836003245e-05
}
34 changes: 34 additions & 0 deletions results/openai__text-embedding-3-large/2/MedrxivClusteringS2S.v2.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
{
"dataset_revision": "35191c8c0dca72d8ff3efcd72aa802307d469663",
"task_name": "MedrxivClusteringS2S.v2",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"v_measures": {
"Level 0": [
0.340695,
0.345533,
0.339033,
0.349097,
0.348423,
0.328494,
0.347611,
0.338524,
0.345661,
0.351792
]
},
"v_measure": 0.343486,
"v_measure_std": 0.006541,
"main_score": 0.343486,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 43.02136588096619,
"kg_co2_emissions": 9.90941361771497e-06
}
Loading
Loading