Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "49c07b6",
"task_name": "BarExamQA",
"mteb_version": "1.38.36",
"scores": {
"test": [
{
"ndcg_at_1": 0.18803,
"ndcg_at_3": 0.23972,
"ndcg_at_5": 0.27503,
"ndcg_at_10": 0.3047,
"ndcg_at_20": 0.33904,
"ndcg_at_100": 0.41306,
"ndcg_at_1000": 0.41432,
"map_at_1": 0.18803,
"map_at_3": 0.22792,
"map_at_5": 0.24758,
"map_at_10": 0.25938,
"map_at_20": 0.26868,
"map_at_100": 0.27863,
"map_at_1000": 0.27871,
"recall_at_1": 0.18803,
"recall_at_3": 0.2735,
"recall_at_5": 0.35897,
"recall_at_10": 0.45299,
"recall_at_20": 0.58974,
"recall_at_100": 0.99145,
"recall_at_1000": 1.0,
"precision_at_1": 0.18803,
"precision_at_3": 0.09117,
"precision_at_5": 0.07179,
"precision_at_10": 0.0453,
"precision_at_20": 0.02949,
"precision_at_100": 0.00991,
"precision_at_1000": 0.001,
"mrr_at_1": 0.188034,
"mrr_at_3": 0.22792,
"mrr_at_5": 0.247578,
"mrr_at_10": 0.259385,
"mrr_at_20": 0.268676,
"mrr_at_100": 0.278631,
"mrr_at_1000": 0.278711,
"nauc_ndcg_at_1_max": 0.116758,
"nauc_ndcg_at_1_std": 0.081966,
"nauc_ndcg_at_1_diff1": 0.16029,
"nauc_ndcg_at_3_max": 0.142485,
"nauc_ndcg_at_3_std": 0.135877,
"nauc_ndcg_at_3_diff1": 0.115892,
"nauc_ndcg_at_5_max": 0.135237,
"nauc_ndcg_at_5_std": 0.132187,
"nauc_ndcg_at_5_diff1": 0.139667,
"nauc_ndcg_at_10_max": 0.119729,
"nauc_ndcg_at_10_std": 0.15334,
"nauc_ndcg_at_10_diff1": 0.127158,
"nauc_ndcg_at_20_max": 0.105152,
"nauc_ndcg_at_20_std": 0.143579,
"nauc_ndcg_at_20_diff1": 0.104659,
"nauc_ndcg_at_100_max": 0.123914,
"nauc_ndcg_at_100_std": 0.139846,
"nauc_ndcg_at_100_diff1": 0.134275,
"nauc_ndcg_at_1000_max": 0.119538,
"nauc_ndcg_at_1000_std": 0.136936,
"nauc_ndcg_at_1000_diff1": 0.130606,
"nauc_map_at_1_max": 0.116758,
"nauc_map_at_1_std": 0.081966,
"nauc_map_at_1_diff1": 0.16029,
"nauc_map_at_3_max": 0.134485,
"nauc_map_at_3_std": 0.124085,
"nauc_map_at_3_diff1": 0.122775,
"nauc_map_at_5_max": 0.130031,
"nauc_map_at_5_std": 0.121472,
"nauc_map_at_5_diff1": 0.135619,
"nauc_map_at_10_max": 0.122303,
"nauc_map_at_10_std": 0.130731,
"nauc_map_at_10_diff1": 0.130472,
"nauc_map_at_20_max": 0.11712,
"nauc_map_at_20_std": 0.128397,
"nauc_map_at_20_diff1": 0.123276,
"nauc_map_at_100_max": 0.120474,
"nauc_map_at_100_std": 0.128028,
"nauc_map_at_100_diff1": 0.130023,
"nauc_map_at_1000_max": 0.120236,
"nauc_map_at_1000_std": 0.127867,
"nauc_map_at_1000_diff1": 0.129824,
"nauc_recall_at_1_max": 0.116758,
"nauc_recall_at_1_std": 0.081966,
"nauc_recall_at_1_diff1": 0.16029,
"nauc_recall_at_3_max": 0.164473,
"nauc_recall_at_3_std": 0.166951,
"nauc_recall_at_3_diff1": 0.098834,
"nauc_recall_at_5_max": 0.148644,
"nauc_recall_at_5_std": 0.15929,
"nauc_recall_at_5_diff1": 0.154624,
"nauc_recall_at_10_max": 0.11051,
"nauc_recall_at_10_std": 0.217224,
"nauc_recall_at_10_diff1": 0.118916,
"nauc_recall_at_20_max": 0.0609,
"nauc_recall_at_20_std": 0.182715,
"nauc_recall_at_20_diff1": 0.037732,
"nauc_recall_at_100_max": 1.0,
"nauc_recall_at_100_std": 0.722475,
"nauc_recall_at_100_diff1": 0.868908,
"nauc_recall_at_1000_max": NaN,
"nauc_recall_at_1000_std": NaN,
"nauc_recall_at_1000_diff1": NaN,
"nauc_precision_at_1_max": 0.116758,
"nauc_precision_at_1_std": 0.081966,
"nauc_precision_at_1_diff1": 0.16029,
"nauc_precision_at_3_max": 0.164473,
"nauc_precision_at_3_std": 0.166951,
"nauc_precision_at_3_diff1": 0.098834,
"nauc_precision_at_5_max": 0.148644,
"nauc_precision_at_5_std": 0.15929,
"nauc_precision_at_5_diff1": 0.154624,
"nauc_precision_at_10_max": 0.11051,
"nauc_precision_at_10_std": 0.217224,
"nauc_precision_at_10_diff1": 0.118916,
"nauc_precision_at_20_max": 0.0609,
"nauc_precision_at_20_std": 0.182715,
"nauc_precision_at_20_diff1": 0.037732,
"nauc_precision_at_100_max": 1.0,
"nauc_precision_at_100_std": 0.722475,
"nauc_precision_at_100_diff1": 0.868908,
"nauc_precision_at_1000_max": 1.0,
"nauc_precision_at_1000_std": 1.0,
"nauc_precision_at_1000_diff1": 1.0,
"nauc_mrr_at_1_max": 0.116758,
"nauc_mrr_at_1_std": 0.081966,
"nauc_mrr_at_1_diff1": 0.16029,
"nauc_mrr_at_3_max": 0.134485,
"nauc_mrr_at_3_std": 0.124085,
"nauc_mrr_at_3_diff1": 0.122775,
"nauc_mrr_at_5_max": 0.130031,
"nauc_mrr_at_5_std": 0.121472,
"nauc_mrr_at_5_diff1": 0.135619,
"nauc_mrr_at_10_max": 0.122303,
"nauc_mrr_at_10_std": 0.130731,
"nauc_mrr_at_10_diff1": 0.130472,
"nauc_mrr_at_20_max": 0.11712,
"nauc_mrr_at_20_std": 0.128397,
"nauc_mrr_at_20_diff1": 0.123276,
"nauc_mrr_at_100_max": 0.120474,
"nauc_mrr_at_100_std": 0.128028,
"nauc_mrr_at_100_diff1": 0.130023,
"nauc_mrr_at_1000_max": 0.120236,
"nauc_mrr_at_1000_std": 0.127867,
"nauc_mrr_at_1000_diff1": 0.129824,
"main_score": 0.3047,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 1.311469316482544,
"kg_co2_emissions": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "49c07b6",
"task_name": "BarExamQA",
"mteb_version": "1.38.36",
"scores": {
"test": [
{
"ndcg_at_1": 0.06838,
"ndcg_at_3": 0.14794,
"ndcg_at_5": 0.16597,
"ndcg_at_10": 0.21254,
"ndcg_at_20": 0.23807,
"ndcg_at_100": 0.32034,
"ndcg_at_1000": 0.32665,
"map_at_1": 0.06838,
"map_at_3": 0.12821,
"map_at_5": 0.13846,
"map_at_10": 0.15745,
"map_at_20": 0.16426,
"map_at_100": 0.17437,
"map_at_1000": 0.17477,
"recall_at_1": 0.06838,
"recall_at_3": 0.20513,
"recall_at_5": 0.24786,
"recall_at_10": 0.39316,
"recall_at_20": 0.49573,
"recall_at_100": 0.95726,
"recall_at_1000": 1.0,
"precision_at_1": 0.06838,
"precision_at_3": 0.06838,
"precision_at_5": 0.04957,
"precision_at_10": 0.03932,
"precision_at_20": 0.02479,
"precision_at_100": 0.00957,
"precision_at_1000": 0.001,
"mrr_at_1": 0.068376,
"mrr_at_3": 0.128205,
"mrr_at_5": 0.138462,
"mrr_at_10": 0.157448,
"mrr_at_20": 0.164257,
"mrr_at_100": 0.174371,
"mrr_at_1000": 0.174766,
"nauc_ndcg_at_1_max": -0.056686,
"nauc_ndcg_at_1_std": -0.075055,
"nauc_ndcg_at_1_diff1": 0.429884,
"nauc_ndcg_at_3_max": -0.013128,
"nauc_ndcg_at_3_std": -0.076145,
"nauc_ndcg_at_3_diff1": 0.299068,
"nauc_ndcg_at_5_max": 0.018024,
"nauc_ndcg_at_5_std": -0.082294,
"nauc_ndcg_at_5_diff1": 0.26625,
"nauc_ndcg_at_10_max": 0.096361,
"nauc_ndcg_at_10_std": 0.013902,
"nauc_ndcg_at_10_diff1": 0.273476,
"nauc_ndcg_at_20_max": 0.096772,
"nauc_ndcg_at_20_std": 0.027902,
"nauc_ndcg_at_20_diff1": 0.244273,
"nauc_ndcg_at_100_max": 0.065563,
"nauc_ndcg_at_100_std": 0.010017,
"nauc_ndcg_at_100_diff1": 0.280752,
"nauc_ndcg_at_1000_max": 0.051758,
"nauc_ndcg_at_1000_std": -0.013613,
"nauc_ndcg_at_1000_diff1": 0.281765,
"nauc_map_at_1_max": -0.056686,
"nauc_map_at_1_std": -0.075055,
"nauc_map_at_1_diff1": 0.429884,
"nauc_map_at_3_max": -0.021425,
"nauc_map_at_3_std": -0.079352,
"nauc_map_at_3_diff1": 0.323667,
"nauc_map_at_5_max": -0.001722,
"nauc_map_at_5_std": -0.083562,
"nauc_map_at_5_diff1": 0.300147,
"nauc_map_at_10_max": 0.035319,
"nauc_map_at_10_std": -0.036885,
"nauc_map_at_10_diff1": 0.300059,
"nauc_map_at_20_max": 0.036842,
"nauc_map_at_20_std": -0.031766,
"nauc_map_at_20_diff1": 0.290117,
"nauc_map_at_100_max": 0.029547,
"nauc_map_at_100_std": -0.036186,
"nauc_map_at_100_diff1": 0.297942,
"nauc_map_at_1000_max": 0.028679,
"nauc_map_at_1000_std": -0.037616,
"nauc_map_at_1000_diff1": 0.298017,
"nauc_recall_at_1_max": -0.056686,
"nauc_recall_at_1_std": -0.075055,
"nauc_recall_at_1_diff1": 0.429884,
"nauc_recall_at_3_max": 0.003504,
"nauc_recall_at_3_std": -0.068991,
"nauc_recall_at_3_diff1": 0.249821,
"nauc_recall_at_5_max": 0.058338,
"nauc_recall_at_5_std": -0.079391,
"nauc_recall_at_5_diff1": 0.200588,
"nauc_recall_at_10_max": 0.223625,
"nauc_recall_at_10_std": 0.123591,
"nauc_recall_at_10_diff1": 0.231663,
"nauc_recall_at_20_max": 0.22116,
"nauc_recall_at_20_std": 0.161661,
"nauc_recall_at_20_diff1": 0.152845,
"nauc_recall_at_100_max": 0.467155,
"nauc_recall_at_100_std": 0.700794,
"nauc_recall_at_100_diff1": 0.248933,
"nauc_recall_at_1000_max": NaN,
"nauc_recall_at_1000_std": NaN,
"nauc_recall_at_1000_diff1": NaN,
"nauc_precision_at_1_max": -0.056686,
"nauc_precision_at_1_std": -0.075055,
"nauc_precision_at_1_diff1": 0.429884,
"nauc_precision_at_3_max": 0.003504,
"nauc_precision_at_3_std": -0.068991,
"nauc_precision_at_3_diff1": 0.249821,
"nauc_precision_at_5_max": 0.058338,
"nauc_precision_at_5_std": -0.079391,
"nauc_precision_at_5_diff1": 0.200588,
"nauc_precision_at_10_max": 0.223625,
"nauc_precision_at_10_std": 0.123591,
"nauc_precision_at_10_diff1": 0.231663,
"nauc_precision_at_20_max": 0.22116,
"nauc_precision_at_20_std": 0.161661,
"nauc_precision_at_20_diff1": 0.152845,
"nauc_precision_at_100_max": 0.467155,
"nauc_precision_at_100_std": 0.700794,
"nauc_precision_at_100_diff1": 0.248933,
"nauc_precision_at_1000_max": 1.0,
"nauc_precision_at_1000_std": 1.0,
"nauc_precision_at_1000_diff1": 1.0,
"nauc_mrr_at_1_max": -0.056686,
"nauc_mrr_at_1_std": -0.075055,
"nauc_mrr_at_1_diff1": 0.429884,
"nauc_mrr_at_3_max": -0.021425,
"nauc_mrr_at_3_std": -0.079352,
"nauc_mrr_at_3_diff1": 0.323667,
"nauc_mrr_at_5_max": -0.001722,
"nauc_mrr_at_5_std": -0.083562,
"nauc_mrr_at_5_diff1": 0.300147,
"nauc_mrr_at_10_max": 0.035319,
"nauc_mrr_at_10_std": -0.036885,
"nauc_mrr_at_10_diff1": 0.300059,
"nauc_mrr_at_20_max": 0.036842,
"nauc_mrr_at_20_std": -0.031766,
"nauc_mrr_at_20_diff1": 0.290117,
"nauc_mrr_at_100_max": 0.029547,
"nauc_mrr_at_100_std": -0.036186,
"nauc_mrr_at_100_diff1": 0.297942,
"nauc_mrr_at_1000_max": 0.028679,
"nauc_mrr_at_1000_std": -0.037616,
"nauc_mrr_at_1000_diff1": 0.298017,
"main_score": 0.21254,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 0.5325167179107666,
"kg_co2_emissions": null
}
Loading