Skip to content
Closed
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 +1,324 @@
{
"dataset_revision": "21bdf1e024bf7c9f46720017559ce2f8c6116507",
"task_name": "ElasticKBRetrieval",
"mteb_version": "2.12.38",
"scores": {
"synthetic_test": [
{
"ndcg_at_1": 0.70213,
"ndcg_at_3": 0.56287,
"ndcg_at_5": 0.53684,
"ndcg_at_10": 0.51354,
"ndcg_at_20": 0.51233,
"ndcg_at_100": 0.55395,
"ndcg_at_1000": 0.61713,
"map_at_1": 0.22897,
"map_at_3": 0.28765,
"map_at_5": 0.3055,
"map_at_10": 0.32613,
"map_at_20": 0.34619,
"map_at_100": 0.37307,
"map_at_1000": 0.38407,
"recall_at_1": 0.22897,
"recall_at_3": 0.3188,
"recall_at_5": 0.35703,
"recall_at_10": 0.40616,
"recall_at_20": 0.47311,
"recall_at_100": 0.64121,
"recall_at_1000": 0.84787,
"accuracy": 0.22897,
"precision_at_1": 0.70213,
"precision_at_3": 0.41489,
"precision_at_5": 0.32979,
"precision_at_10": 0.23245,
"precision_at_20": 0.16755,
"precision_at_100": 0.06553,
"precision_at_1000": 0.01234,
"mrr_at_1": 0.702128,
"mrr_at_3": 0.782801,
"mrr_at_5": 0.793706,
"mrr_at_10": 0.797716,
"mrr_at_20": 0.799809,
"mrr_at_100": 0.800236,
"mrr_at_1000": 0.800236,
"nauc_ndcg_at_1_max": 0.03637,
"nauc_ndcg_at_1_std": -0.155315,
"nauc_ndcg_at_1_diff1": 0.393593,
"nauc_ndcg_at_3_max": 0.101207,
"nauc_ndcg_at_3_std": 0.059933,
"nauc_ndcg_at_3_diff1": 0.133793,
"nauc_ndcg_at_5_max": 0.10129,
"nauc_ndcg_at_5_std": 0.063464,
"nauc_ndcg_at_5_diff1": 0.172103,
"nauc_ndcg_at_10_max": 0.13233,
"nauc_ndcg_at_10_std": 0.08067,
"nauc_ndcg_at_10_diff1": 0.262056,
"nauc_ndcg_at_20_max": 0.177488,
"nauc_ndcg_at_20_std": 0.101258,
"nauc_ndcg_at_20_diff1": 0.292539,
"nauc_ndcg_at_100_max": 0.238721,
"nauc_ndcg_at_100_std": 0.174771,
"nauc_ndcg_at_100_diff1": 0.304403,
"nauc_ndcg_at_1000_max": 0.223684,
"nauc_ndcg_at_1000_std": 0.186361,
"nauc_ndcg_at_1000_diff1": 0.266568,
"nauc_map_at_1_max": 0.09017,
"nauc_map_at_1_std": -0.011468,
"nauc_map_at_1_diff1": 0.49284,
"nauc_map_at_3_max": 0.122122,
"nauc_map_at_3_std": -0.012008,
"nauc_map_at_3_diff1": 0.428711,
"nauc_map_at_5_max": 0.119363,
"nauc_map_at_5_std": -0.013921,
"nauc_map_at_5_diff1": 0.41813,
"nauc_map_at_10_max": 0.139708,
"nauc_map_at_10_std": 0.006488,
"nauc_map_at_10_diff1": 0.406346,
"nauc_map_at_20_max": 0.178808,
"nauc_map_at_20_std": 0.052469,
"nauc_map_at_20_diff1": 0.374139,
"nauc_map_at_100_max": 0.20081,
"nauc_map_at_100_std": 0.100564,
"nauc_map_at_100_diff1": 0.348661,
"nauc_map_at_1000_max": 0.197797,
"nauc_map_at_1000_std": 0.109939,
"nauc_map_at_1000_diff1": 0.340116,
"nauc_recall_at_1_max": 0.09017,
"nauc_recall_at_1_std": -0.011468,
"nauc_recall_at_1_diff1": 0.49284,
"nauc_recall_at_3_max": 0.106298,
"nauc_recall_at_3_std": -0.002766,
"nauc_recall_at_3_diff1": 0.366062,
"nauc_recall_at_5_max": 0.097266,
"nauc_recall_at_5_std": -0.015098,
"nauc_recall_at_5_diff1": 0.357176,
"nauc_recall_at_10_max": 0.13274,
"nauc_recall_at_10_std": 0.018272,
"nauc_recall_at_10_diff1": 0.350881,
"nauc_recall_at_20_max": 0.198021,
"nauc_recall_at_20_std": 0.098643,
"nauc_recall_at_20_diff1": 0.266127,
"nauc_recall_at_100_max": 0.237467,
"nauc_recall_at_100_std": 0.235715,
"nauc_recall_at_100_diff1": 0.219191,
"nauc_recall_at_1000_max": 0.194755,
"nauc_recall_at_1000_std": 0.259497,
"nauc_recall_at_1000_diff1": 0.214908,
"nauc_precision_at_1_max": 0.03637,
"nauc_precision_at_1_std": -0.155315,
"nauc_precision_at_1_diff1": 0.393593,
"nauc_precision_at_3_max": 0.102194,
"nauc_precision_at_3_std": 0.115327,
"nauc_precision_at_3_diff1": -0.232675,
"nauc_precision_at_5_max": 0.051921,
"nauc_precision_at_5_std": 0.125716,
"nauc_precision_at_5_diff1": -0.311005,
"nauc_precision_at_10_max": 0.078458,
"nauc_precision_at_10_std": 0.209922,
"nauc_precision_at_10_diff1": -0.328814,
"nauc_precision_at_20_max": 0.134614,
"nauc_precision_at_20_std": 0.300578,
"nauc_precision_at_20_diff1": -0.390179,
"nauc_precision_at_100_max": -0.012795,
"nauc_precision_at_100_std": 0.249381,
"nauc_precision_at_100_diff1": -0.371273,
"nauc_precision_at_1000_max": -0.173382,
"nauc_precision_at_1000_std": 0.063768,
"nauc_precision_at_1000_diff1": -0.303265,
"nauc_mrr_at_1_max": 0.03637,
"nauc_mrr_at_1_std": -0.155315,
"nauc_mrr_at_1_diff1": 0.393593,
"nauc_mrr_at_3_max": 0.087938,
"nauc_mrr_at_3_std": -0.079861,
"nauc_mrr_at_3_diff1": 0.326316,
"nauc_mrr_at_5_max": 0.080416,
"nauc_mrr_at_5_std": -0.089234,
"nauc_mrr_at_5_diff1": 0.347435,
"nauc_mrr_at_10_max": 0.084397,
"nauc_mrr_at_10_std": -0.089832,
"nauc_mrr_at_10_diff1": 0.359597,
"nauc_mrr_at_20_max": 0.079692,
"nauc_mrr_at_20_std": -0.094003,
"nauc_mrr_at_20_diff1": 0.354783,
"nauc_mrr_at_100_max": 0.078293,
"nauc_mrr_at_100_std": -0.094719,
"nauc_mrr_at_100_diff1": 0.354029,
"nauc_mrr_at_1000_max": 0.078293,
"nauc_mrr_at_1000_std": -0.094719,
"nauc_mrr_at_1000_diff1": 0.354029,
"hit_rate_at_1": 0.70213,
"hit_rate_at_3": 0.87766,
"hit_rate_at_5": 0.92553,
"hit_rate_at_10": 0.95213,
"hit_rate_at_20": 0.98404,
"hit_rate_at_100": 1.0,
"hit_rate_at_1000": 1.0,
"main_score": 0.51354,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
],
"real_chat_test": [
{
"ndcg_at_1": 0.73276,
"ndcg_at_3": 0.65531,
"ndcg_at_5": 0.61008,
"ndcg_at_10": 0.55386,
"ndcg_at_20": 0.51278,
"ndcg_at_100": 0.46226,
"ndcg_at_1000": 0.54149,
"map_at_1": 0.05417,
"map_at_3": 0.09937,
"map_at_5": 0.11647,
"map_at_10": 0.13877,
"map_at_20": 0.15862,
"map_at_100": 0.2014,
"map_at_1000": 0.25157,
"recall_at_1": 0.05417,
"recall_at_3": 0.11056,
"recall_at_5": 0.13696,
"recall_at_10": 0.17956,
"recall_at_20": 0.22769,
"recall_at_100": 0.37549,
"recall_at_1000": 0.69322,
"accuracy": 0.05417,
"precision_at_1": 0.73276,
"precision_at_3": 0.62069,
"precision_at_5": 0.54828,
"precision_at_10": 0.45216,
"precision_at_20": 0.36789,
"precision_at_100": 0.21707,
"precision_at_1000": 0.07642,
"mrr_at_1": 0.732759,
"mrr_at_3": 0.801724,
"mrr_at_5": 0.809483,
"mrr_at_10": 0.814426,
"mrr_at_20": 0.816045,
"mrr_at_100": 0.816574,
"mrr_at_1000": 0.816599,
"nauc_ndcg_at_1_max": 0.392414,
"nauc_ndcg_at_1_std": 0.239732,
"nauc_ndcg_at_1_diff1": 0.408702,
"nauc_ndcg_at_3_max": 0.31895,
"nauc_ndcg_at_3_std": 0.168499,
"nauc_ndcg_at_3_diff1": 0.194345,
"nauc_ndcg_at_5_max": 0.311744,
"nauc_ndcg_at_5_std": 0.183467,
"nauc_ndcg_at_5_diff1": 0.140404,
"nauc_ndcg_at_10_max": 0.338781,
"nauc_ndcg_at_10_std": 0.251598,
"nauc_ndcg_at_10_diff1": 0.137225,
"nauc_ndcg_at_20_max": 0.350291,
"nauc_ndcg_at_20_std": 0.276095,
"nauc_ndcg_at_20_diff1": 0.148665,
"nauc_ndcg_at_100_max": 0.433396,
"nauc_ndcg_at_100_std": 0.28703,
"nauc_ndcg_at_100_diff1": 0.243558,
"nauc_ndcg_at_1000_max": 0.423155,
"nauc_ndcg_at_1000_std": 0.328531,
"nauc_ndcg_at_1000_diff1": 0.255891,
"nauc_map_at_1_max": 0.372885,
"nauc_map_at_1_std": -0.034218,
"nauc_map_at_1_diff1": 0.564564,
"nauc_map_at_3_max": 0.323696,
"nauc_map_at_3_std": -0.087526,
"nauc_map_at_3_diff1": 0.428836,
"nauc_map_at_5_max": 0.323596,
"nauc_map_at_5_std": -0.095468,
"nauc_map_at_5_diff1": 0.414677,
"nauc_map_at_10_max": 0.351467,
"nauc_map_at_10_std": -0.051137,
"nauc_map_at_10_diff1": 0.405714,
"nauc_map_at_20_max": 0.358121,
"nauc_map_at_20_std": -0.024856,
"nauc_map_at_20_diff1": 0.390702,
"nauc_map_at_100_max": 0.405742,
"nauc_map_at_100_std": 0.093437,
"nauc_map_at_100_diff1": 0.350073,
"nauc_map_at_1000_max": 0.4367,
"nauc_map_at_1000_std": 0.226577,
"nauc_map_at_1000_diff1": 0.299833,
"nauc_recall_at_1_max": 0.372885,
"nauc_recall_at_1_std": -0.034218,
"nauc_recall_at_1_diff1": 0.564564,
"nauc_recall_at_3_max": 0.26701,
"nauc_recall_at_3_std": -0.114567,
"nauc_recall_at_3_diff1": 0.380972,
"nauc_recall_at_5_max": 0.251532,
"nauc_recall_at_5_std": -0.126484,
"nauc_recall_at_5_diff1": 0.356845,
"nauc_recall_at_10_max": 0.297609,
"nauc_recall_at_10_std": -0.049554,
"nauc_recall_at_10_diff1": 0.349745,
"nauc_recall_at_20_max": 0.289278,
"nauc_recall_at_20_std": -0.024984,
"nauc_recall_at_20_diff1": 0.316856,
"nauc_recall_at_100_max": 0.310333,
"nauc_recall_at_100_std": 0.110186,
"nauc_recall_at_100_diff1": 0.245096,
"nauc_recall_at_1000_max": 0.286375,
"nauc_recall_at_1000_std": 0.283108,
"nauc_recall_at_1000_diff1": 0.152341,
"nauc_precision_at_1_max": 0.392414,
"nauc_precision_at_1_std": 0.239732,
"nauc_precision_at_1_diff1": 0.408702,
"nauc_precision_at_3_max": 0.263014,
"nauc_precision_at_3_std": 0.165473,
"nauc_precision_at_3_diff1": 0.082503,
"nauc_precision_at_5_max": 0.228145,
"nauc_precision_at_5_std": 0.192415,
"nauc_precision_at_5_diff1": -0.016206,
"nauc_precision_at_10_max": 0.19358,
"nauc_precision_at_10_std": 0.281694,
"nauc_precision_at_10_diff1": -0.094217,
"nauc_precision_at_20_max": 0.11416,
"nauc_precision_at_20_std": 0.329075,
"nauc_precision_at_20_diff1": -0.169462,
"nauc_precision_at_100_max": 0.079117,
"nauc_precision_at_100_std": 0.372067,
"nauc_precision_at_100_diff1": -0.195606,
"nauc_precision_at_1000_max": 0.005204,
"nauc_precision_at_1000_std": 0.233734,
"nauc_precision_at_1000_diff1": -0.169497,
"nauc_mrr_at_1_max": 0.392414,
"nauc_mrr_at_1_std": 0.239732,
"nauc_mrr_at_1_diff1": 0.408702,
"nauc_mrr_at_3_max": 0.41073,
"nauc_mrr_at_3_std": 0.232272,
"nauc_mrr_at_3_diff1": 0.409098,
"nauc_mrr_at_5_max": 0.397771,
"nauc_mrr_at_5_std": 0.225726,
"nauc_mrr_at_5_diff1": 0.4051,
"nauc_mrr_at_10_max": 0.407635,
"nauc_mrr_at_10_std": 0.224537,
"nauc_mrr_at_10_diff1": 0.410387,
"nauc_mrr_at_20_max": 0.407774,
"nauc_mrr_at_20_std": 0.224568,
"nauc_mrr_at_20_diff1": 0.410494,
"nauc_mrr_at_100_max": 0.407187,
"nauc_mrr_at_100_std": 0.226996,
"nauc_mrr_at_100_diff1": 0.409546,
"nauc_mrr_at_1000_max": 0.407195,
"nauc_mrr_at_1000_std": 0.226923,
"nauc_mrr_at_1000_diff1": 0.409689,
"hit_rate_at_1": 0.73276,
"hit_rate_at_3": 0.88793,
"hit_rate_at_5": 0.92241,
"hit_rate_at_10": 0.9569,
"hit_rate_at_20": 0.97845,
"hit_rate_at_100": 0.99569,
"hit_rate_at_1000": 1.0,
"main_score": 0.55386,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 470.54601192474365,
"kg_co2_emissions": null,
"date": 1777843190.525151
}
Loading
Loading