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 +1,168 @@
{
"dataset_revision": "c5691e3c48741d5f83b5cc8e630653d7a8cfc048",
"task_name": "AskUbuntuDupQuestions",
"mteb_version": "2.14.2",
"scores": {
"test": [
{
"ndcg_at_1": 0.66482,
"ndcg_at_3": 0.62647,
"ndcg_at_5": 0.63504,
"ndcg_at_10": 0.68505,
"ndcg_at_20": 0.78099,
"ndcg_at_100": 0.78099,
"ndcg_at_1000": 0.78099,
"map_at_1": 0.18717,
"map_at_3": 0.33961,
"map_at_5": 0.42372,
"map_at_10": 0.53432,
"map_at_20": 0.63339,
"map_at_100": 0.63339,
"map_at_1000": 0.63339,
"recall_at_1": 0.18717,
"recall_at_3": 0.38516,
"recall_at_5": 0.52825,
"recall_at_10": 0.7541,
"recall_at_20": 1.0,
"recall_at_100": 1.0,
"recall_at_1000": 1.0,
"accuracy": 0.18717,
"precision_at_1": 0.66482,
"precision_at_3": 0.54571,
"precision_at_5": 0.48366,
"precision_at_10": 0.37701,
"precision_at_20": 0.27355,
"precision_at_100": 0.05471,
"precision_at_1000": 0.00547,
"mrr_at_1": 0.66482,
"mrr_at_3": 0.740074,
"mrr_at_5": 0.758356,
"mrr_at_10": 0.764829,
"mrr_at_20": 0.767216,
"mrr_at_100": 0.767216,
"mrr_at_1000": 0.767216,
"nauc_ndcg_at_1_max": 0.423653,
"nauc_ndcg_at_1_std": 0.173072,
"nauc_ndcg_at_1_diff1": 0.222272,
"nauc_ndcg_at_3_max": 0.277909,
"nauc_ndcg_at_3_std": 0.11991,
"nauc_ndcg_at_3_diff1": 0.107609,
"nauc_ndcg_at_5_max": 0.231119,
"nauc_ndcg_at_5_std": 0.158971,
"nauc_ndcg_at_5_diff1": 0.117982,
"nauc_ndcg_at_10_max": 0.221373,
"nauc_ndcg_at_10_std": 0.187953,
"nauc_ndcg_at_10_diff1": 0.113751,
"nauc_ndcg_at_20_max": 0.297367,
"nauc_ndcg_at_20_std": 0.14789,
"nauc_ndcg_at_20_diff1": 0.129165,
"nauc_ndcg_at_100_max": 0.297367,
"nauc_ndcg_at_100_std": 0.14789,
"nauc_ndcg_at_100_diff1": 0.129165,
"nauc_ndcg_at_1000_max": 0.297367,
"nauc_ndcg_at_1000_std": 0.14789,
"nauc_ndcg_at_1000_diff1": 0.129165,
"nauc_map_at_1_max": -0.023294,
"nauc_map_at_1_std": -0.052223,
"nauc_map_at_1_diff1": 0.291834,
"nauc_map_at_3_max": 0.016135,
"nauc_map_at_3_std": 0.049953,
"nauc_map_at_3_diff1": 0.194425,
"nauc_map_at_5_max": 0.049903,
"nauc_map_at_5_std": 0.119845,
"nauc_map_at_5_diff1": 0.16692,
"nauc_map_at_10_max": 0.137264,
"nauc_map_at_10_std": 0.167395,
"nauc_map_at_10_diff1": 0.124031,
"nauc_map_at_20_max": 0.230845,
"nauc_map_at_20_std": 0.138121,
"nauc_map_at_20_diff1": 0.106685,
"nauc_map_at_100_max": 0.230845,
"nauc_map_at_100_std": 0.138121,
"nauc_map_at_100_diff1": 0.106685,
"nauc_map_at_1000_max": 0.230845,
"nauc_map_at_1000_std": 0.138121,
"nauc_map_at_1000_diff1": 0.106685,
"nauc_recall_at_1_max": -0.023294,
"nauc_recall_at_1_std": -0.052223,
"nauc_recall_at_1_diff1": 0.291834,
"nauc_recall_at_3_max": -0.041312,
"nauc_recall_at_3_std": 0.058926,
"nauc_recall_at_3_diff1": 0.157202,
"nauc_recall_at_5_max": -0.058658,
"nauc_recall_at_5_std": 0.142264,
"nauc_recall_at_5_diff1": 0.131672,
"nauc_recall_at_10_max": -0.03862,
"nauc_recall_at_10_std": 0.212311,
"nauc_recall_at_10_diff1": 0.071836,
"nauc_recall_at_20_max": NaN,
"nauc_recall_at_20_std": NaN,
"nauc_recall_at_20_diff1": NaN,
"nauc_recall_at_100_max": NaN,
"nauc_recall_at_100_std": NaN,
"nauc_recall_at_100_diff1": NaN,
"nauc_recall_at_1000_max": NaN,
"nauc_recall_at_1000_std": NaN,
"nauc_recall_at_1000_diff1": NaN,
"nauc_precision_at_1_max": 0.423653,
"nauc_precision_at_1_std": 0.173072,
"nauc_precision_at_1_diff1": 0.222272,
"nauc_precision_at_3_max": 0.305751,
"nauc_precision_at_3_std": 0.169266,
"nauc_precision_at_3_diff1": -0.038888,
"nauc_precision_at_5_max": 0.307209,
"nauc_precision_at_5_std": 0.19991,
"nauc_precision_at_5_diff1": -0.081413,
"nauc_precision_at_10_max": 0.298447,
"nauc_precision_at_10_std": 0.128564,
"nauc_precision_at_10_diff1": -0.121246,
"nauc_precision_at_20_max": 0.265044,
"nauc_precision_at_20_std": 0.023607,
"nauc_precision_at_20_diff1": -0.101464,
"nauc_precision_at_100_max": 0.265044,
"nauc_precision_at_100_std": 0.023607,
"nauc_precision_at_100_diff1": -0.101464,
"nauc_precision_at_1000_max": 0.265044,
"nauc_precision_at_1000_std": 0.023607,
"nauc_precision_at_1000_diff1": -0.101464,
"nauc_mrr_at_1_max": 0.423653,
"nauc_mrr_at_1_std": 0.173072,
"nauc_mrr_at_1_diff1": 0.222272,
"nauc_mrr_at_3_max": 0.397737,
"nauc_mrr_at_3_std": 0.164426,
"nauc_mrr_at_3_diff1": 0.21912,
"nauc_mrr_at_5_max": 0.4049,
"nauc_mrr_at_5_std": 0.174712,
"nauc_mrr_at_5_diff1": 0.225207,
"nauc_mrr_at_10_max": 0.40803,
"nauc_mrr_at_10_std": 0.174824,
"nauc_mrr_at_10_diff1": 0.223717,
"nauc_mrr_at_20_max": 0.408129,
"nauc_mrr_at_20_std": 0.172028,
"nauc_mrr_at_20_diff1": 0.223985,
"nauc_mrr_at_100_max": 0.408129,
"nauc_mrr_at_100_std": 0.172028,
"nauc_mrr_at_100_diff1": 0.223985,
"nauc_mrr_at_1000_max": 0.408129,
"nauc_mrr_at_1000_std": 0.172028,
"nauc_mrr_at_1000_diff1": 0.223985,
"hit_rate_at_1": 0.66482,
"hit_rate_at_3": 0.83657,
"hit_rate_at_5": 0.9169,
"hit_rate_at_10": 0.96676,
"hit_rate_at_20": 1.0,
"hit_rate_at_100": 1.0,
"hit_rate_at_1000": 1.0,
"main_score": 0.63339,
"hf_subset": "default",
"languages": [
"eng-Latn"
],
"mteb_version": "2.14.2"
}
]
},
"evaluation_time": 26.280765056610107,
"kg_co2_emissions": null,
"date": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
{
"dataset_revision": "d3fb88f8f02e40887cd149695127462bbcf29b4a",
"task_name": "BIOSSES",
"mteb_version": "2.14.2",
"scores": {
"test": [
{
"pearson": 0.891985,
"spearman": 0.871713,
"cosine_pearson": 0.891985,
"cosine_spearman": 0.871713,
"manhattan_pearson": 0.867763,
"manhattan_spearman": 0.865923,
"euclidean_pearson": 0.866928,
"euclidean_spearman": 0.863255,
"main_score": 0.871713,
"hf_subset": "default",
"languages": [
"eng-Latn"
],
"mteb_version": "2.14.2"
}
]
},
"evaluation_time": 0.7296950817108154,
"kg_co2_emissions": null,
"date": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,141 @@
{
"dataset_revision": "0fd18e25b25c072e09e0d92ab615fda904d66300",
"task_name": "Banking77Classification",
"mteb_version": "2.14.2",
"scores": {
"test": [
{
"scores_per_experiment": [
{
"accuracy": 0.866558,
"f1": 0.865713,
"f1_weighted": 0.865713,
"precision": 0.872529,
"precision_weighted": 0.872529,
"recall": 0.866558,
"recall_weighted": 0.866558,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.852597,
"f1": 0.851841,
"f1_weighted": 0.851841,
"precision": 0.859928,
"precision_weighted": 0.859928,
"recall": 0.852597,
"recall_weighted": 0.852597,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.855519,
"f1": 0.854478,
"f1_weighted": 0.854478,
"precision": 0.863074,
"precision_weighted": 0.863074,
"recall": 0.855519,
"recall_weighted": 0.855519,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.856494,
"f1": 0.856905,
"f1_weighted": 0.856905,
"precision": 0.866001,
"precision_weighted": 0.866001,
"recall": 0.856494,
"recall_weighted": 0.856494,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.840909,
"f1": 0.840373,
"f1_weighted": 0.840373,
"precision": 0.848296,
"precision_weighted": 0.848296,
"recall": 0.840909,
"recall_weighted": 0.840909,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.841234,
"f1": 0.839522,
"f1_weighted": 0.839522,
"precision": 0.849815,
"precision_weighted": 0.849815,
"recall": 0.841234,
"recall_weighted": 0.841234,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.847078,
"f1": 0.846543,
"f1_weighted": 0.846543,
"precision": 0.85567,
"precision_weighted": 0.85567,
"recall": 0.847078,
"recall_weighted": 0.847078,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.840909,
"f1": 0.840544,
"f1_weighted": 0.840544,
"precision": 0.854732,
"precision_weighted": 0.854732,
"recall": 0.840909,
"recall_weighted": 0.840909,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.849675,
"f1": 0.848443,
"f1_weighted": 0.848443,
"precision": 0.857718,
"precision_weighted": 0.857718,
"recall": 0.849675,
"recall_weighted": 0.849675,
"ap": null,
"ap_weighted": null
},
{
"accuracy": 0.846429,
"f1": 0.844605,
"f1_weighted": 0.844605,
"precision": 0.854198,
"precision_weighted": 0.854198,
"recall": 0.846429,
"recall_weighted": 0.846429,
"ap": null,
"ap_weighted": null
}
],
"accuracy": 0.84974,
"f1": 0.848897,
"f1_weighted": 0.848897,
"precision": 0.858196,
"precision_weighted": 0.858196,
"recall": 0.84974,
"recall_weighted": 0.84974,
"ap": NaN,
"ap_weighted": NaN,
"main_score": 0.84974,
"hf_subset": "default",
"languages": [
"eng-Latn"
],
"mteb_version": "2.14.2"
}
]
},
"evaluation_time": 79.30222415924072,
"kg_co2_emissions": null,
"date": null
}
Loading
Loading