{ "dataset_revision": "1f7e6a9d6fa6e64c53d146e428565640410c0df1", "task_name": "AmazonCounterfactualClassification", "mteb_version": "2.10.7", "scores": { "validation": [ { "scores_per_experiment": [ { "accuracy": 0.660661, "f1": 0.539131, "f1_weighted": 0.728177, "precision": 0.573326, "precision_weighted": 0.878998, "recall": 0.692049, "recall_weighted": 0.660661, "ap": 0.166466, "ap_weighted": 0.166466 }, { "accuracy": 0.645646, "f1": 0.520741, "f1_weighted": 0.71618, "precision": 0.559846, "precision_weighted": 0.868262, "recall": 0.65719, "recall_weighted": 0.645646, "ap": 0.149728, "ap_weighted": 0.149728 }, { "accuracy": 0.668168, "f1": 0.557558, "f1_weighted": 0.734269, "precision": 0.591513, "precision_weighted": 0.895845, "recall": 0.742618, "recall_weighted": 0.668168, "ap": 0.192479, "ap_weighted": 0.192479 }, { "accuracy": 0.611111, "f1": 0.509608, "f1_weighted": 0.687825, "precision": 0.567568, "precision_weighted": 0.88061, "recall": 0.684387, "recall_weighted": 0.611111, "ap": 0.158868, "ap_weighted": 0.158868 }, { "accuracy": 0.678679, "f1": 0.554128, "f1_weighted": 0.74237, "precision": 0.580928, "precision_weighted": 0.883273, "recall": 0.708694, "recall_weighted": 0.678679, "ap": 0.176592, "ap_weighted": 0.176592 }, { "accuracy": 0.60961, "f1": 0.498029, "f1_weighted": 0.687077, "precision": 0.553143, "precision_weighted": 0.866063, "recall": 0.643784, "recall_weighted": 0.60961, "ap": 0.142346, "ap_weighted": 0.142346 }, { "accuracy": 0.593093, "f1": 0.490376, "f1_weighted": 0.673137, "precision": 0.554044, "precision_weighted": 0.868805, "recall": 0.647858, "recall_weighted": 0.593093, "ap": 0.143155, "ap_weighted": 0.143155 }, { "accuracy": 0.65015, "f1": 0.525848, "f1_weighted": 0.719774, "precision": 0.563412, "precision_weighted": 0.871043, "recall": 0.666322, "recall_weighted": 0.65015, "ap": 0.153943, "ap_weighted": 0.153943 }, { "accuracy": 0.668168, "f1": 0.555774, "f1_weighted": 0.734263, "precision": 0.589241, "precision_weighted": 0.89351, "recall": 0.73599, "recall_weighted": 0.668168, "ap": 0.189038, "ap_weighted": 0.189038 }, { "accuracy": 0.638138, "f1": 0.517518, "f1_weighted": 0.710221, "precision": 0.560216, "precision_weighted": 0.869578, "recall": 0.659644, "recall_weighted": 0.638138, "ap": 0.150261, "ap_weighted": 0.150261 } ], "accuracy": 0.642342, "f1": 0.526871, "f1_weighted": 0.713329, "precision": 0.569324, "precision_weighted": 0.877599, "recall": 0.683854, "recall_weighted": 0.642342, "ap": 0.162288, "ap_weighted": 0.162288, "main_score": 0.642342, "hf_subset": "en-ext", "languages": [ "eng-Latn" ] }, { "scores_per_experiment": [ { "accuracy": 0.570149, "f1": 0.519254, "f1_weighted": 0.621512, "precision": 0.571126, "precision_weighted": 0.784947, "recall": 0.624206, "recall_weighted": 0.570149, "ap": 0.223263, "ap_weighted": 0.223263 }, { "accuracy": 0.641791, "f1": 0.577127, "f1_weighted": 0.685229, "precision": 0.601508, "precision_weighted": 0.806672, "recall": 0.674343, "recall_weighted": 0.641791, "ap": 0.256075, "ap_weighted": 0.256075 }, { "accuracy": 0.58209, "f1": 0.511946, "f1_weighted": 0.632902, "precision": 0.548468, "precision_weighted": 0.75884, "recall": 0.583717, "recall_weighted": 0.58209, "ap": 0.204515, "ap_weighted": 0.204515 }, { "accuracy": 0.638806, "f1": 0.57242, "f1_weighted": 0.68256, "precision": 0.596642, "precision_weighted": 0.801838, "recall": 0.665723, "recall_weighted": 0.638806, "ap": 0.250627, "ap_weighted": 0.250627 }, { "accuracy": 0.626866, "f1": 0.567626, "f1_weighted": 0.672251, "precision": 0.599314, "precision_weighted": 0.807376, "recall": 0.672134, "recall_weighted": 0.626866, "ap": 0.253138, "ap_weighted": 0.253138 }, { "accuracy": 0.662687, "f1": 0.556364, "f1_weighted": 0.698343, "precision": 0.563003, "precision_weighted": 0.763284, "recall": 0.598375, "recall_weighted": 0.662687, "ap": 0.214886, "ap_weighted": 0.214886 }, { "accuracy": 0.653731, "f1": 0.571157, "f1_weighted": 0.694176, "precision": 0.584803, "precision_weighted": 0.786074, "recall": 0.64067, "recall_weighted": 0.653731, "ap": 0.237555, "ap_weighted": 0.237555 }, { "accuracy": 0.683582, "f1": 0.591576, "f1_weighted": 0.718301, "precision": 0.59531, "precision_weighted": 0.790579, "recall": 0.651905, "recall_weighted": 0.683582, "ap": 0.247646, "ap_weighted": 0.247646 }, { "accuracy": 0.647761, "f1": 0.579468, "f1_weighted": 0.690255, "precision": 0.600325, "precision_weighted": 0.804022, "recall": 0.671138, "recall_weighted": 0.647761, "ap": 0.25485, "ap_weighted": 0.25485 }, { "accuracy": 0.620896, "f1": 0.532005, "f1_weighted": 0.665341, "precision": 0.552144, "precision_weighted": 0.758398, "recall": 0.586736, "recall_weighted": 0.620896, "ap": 0.207078, "ap_weighted": 0.207078 } ], "accuracy": 0.632836, "f1": 0.557894, "f1_weighted": 0.676087, "precision": 0.581264, "precision_weighted": 0.786203, "recall": 0.636895, "recall_weighted": 0.632836, "ap": 0.234963, "ap_weighted": 0.234963, "main_score": 0.632836, "hf_subset": "en", "languages": [ "eng-Latn" ] } ], "test": [ { "scores_per_experiment": [ { "accuracy": 0.696402, "f1": 0.574988, "f1_weighted": 0.75481, "precision": 0.593841, "precision_weighted": 0.886556, "recall": 0.732004, "recall_weighted": 0.696402, "ap": 0.197333, "ap_weighted": 0.197333 }, { "accuracy": 0.666417, "f1": 0.54214, "f1_weighted": 0.730969, "precision": 0.57182, "precision_weighted": 0.870904, "recall": 0.680302, "recall_weighted": 0.666417, "ap": 0.166866, "ap_weighted": 0.166866 }, { "accuracy": 0.670915, "f1": 0.557661, "f1_weighted": 0.73484, "precision": 0.587956, "precision_weighted": 0.88593, "recall": 0.724135, "recall_weighted": 0.670915, "ap": 0.189144, "ap_weighted": 0.189144 }, { "accuracy": 0.598951, "f1": 0.498513, "f1_weighted": 0.676171, "precision": 0.558633, "precision_weighted": 0.86715, "recall": 0.65536, "recall_weighted": 0.598951, "ap": 0.151209, "ap_weighted": 0.151209 }, { "accuracy": 0.682159, "f1": 0.562336, "f1_weighted": 0.743615, "precision": 0.586927, "precision_weighted": 0.882707, "recall": 0.717697, "recall_weighted": 0.682159, "ap": 0.187383, "ap_weighted": 0.187383 }, { "accuracy": 0.632684, "f1": 0.526379, "f1_weighted": 0.704002, "precision": 0.572738, "precision_weighted": 0.877078, "recall": 0.690082, "recall_weighted": 0.632684, "ap": 0.168316, "ap_weighted": 0.168316 }, { "accuracy": 0.642429, "f1": 0.533331, "f1_weighted": 0.711947, "precision": 0.575318, "precision_weighted": 0.878178, "recall": 0.695521, "recall_weighted": 0.642429, "ap": 0.17171, "ap_weighted": 0.17171 }, { "accuracy": 0.681409, "f1": 0.558913, "f1_weighted": 0.742919, "precision": 0.583297, "precision_weighted": 0.879316, "recall": 0.707742, "recall_weighted": 0.681409, "ap": 0.182116, "ap_weighted": 0.182116 }, { "accuracy": 0.708396, "f1": 0.590859, "f1_weighted": 0.764452, "precision": 0.60574, "precision_weighted": 0.895591, "recall": 0.760949, "recall_weighted": 0.708396, "ap": 0.216207, "ap_weighted": 0.216207 }, { "accuracy": 0.68066, "f1": 0.560272, "f1_weighted": 0.742406, "precision": 0.585323, "precision_weighted": 0.881427, "recall": 0.713681, "recall_weighted": 0.68066, "ap": 0.185078, "ap_weighted": 0.185078 } ], "accuracy": 0.666042, "f1": 0.550539, "f1_weighted": 0.730613, "precision": 0.582159, "precision_weighted": 0.880484, "recall": 0.707747, "recall_weighted": 0.666042, "ap": 0.181536, "ap_weighted": 0.181536, "main_score": 0.666042, "hf_subset": "en-ext", "languages": [ "eng-Latn" ] }, { "scores_per_experiment": [ { "accuracy": 0.616418, "f1": 0.571465, "f1_weighted": 0.655985, "precision": 0.60476, "precision_weighted": 0.787698, "recall": 0.666254, "recall_weighted": 0.616418, "ap": 0.276934, "ap_weighted": 0.276934 }, { "accuracy": 0.689552, "f1": 0.629362, "f1_weighted": 0.720316, "precision": 0.634798, "precision_weighted": 0.804039, "recall": 0.70593, "recall_weighted": 0.689552, "ap": 0.313767, "ap_weighted": 0.313767 }, { "accuracy": 0.643284, "f1": 0.588222, "f1_weighted": 0.679916, "precision": 0.607631, "precision_weighted": 0.785023, "recall": 0.668505, "recall_weighted": 0.643284, "ap": 0.281284, "ap_weighted": 0.281284 }, { "accuracy": 0.662687, "f1": 0.609134, "f1_weighted": 0.697237, "precision": 0.624849, "precision_weighted": 0.800277, "recall": 0.695011, "recall_weighted": 0.662687, "ap": 0.301188, "ap_weighted": 0.301188 }, { "accuracy": 0.646269, "f1": 0.596647, "f1_weighted": 0.682799, "precision": 0.619113, "precision_weighted": 0.797814, "recall": 0.687696, "recall_weighted": 0.646269, "ap": 0.293869, "ap_weighted": 0.293869 }, { "accuracy": 0.695522, "f1": 0.631093, "f1_weighted": 0.724976, "precision": 0.633308, "precision_weighted": 0.800305, "recall": 0.700973, "recall_weighted": 0.695522, "ap": 0.311631, "ap_weighted": 0.311631 }, { "accuracy": 0.720896, "f1": 0.637743, "f1_weighted": 0.743432, "precision": 0.63047, "precision_weighted": 0.788135, "recall": 0.682073, "recall_weighted": 0.720896, "ap": 0.30437, "ap_weighted": 0.30437 }, { "accuracy": 0.698507, "f1": 0.624156, "f1_weighted": 0.725953, "precision": 0.622735, "precision_weighted": 0.787177, "recall": 0.679715, "recall_weighted": 0.698507, "ap": 0.297506, "ap_weighted": 0.297506 }, { "accuracy": 0.610448, "f1": 0.55892, "f1_weighted": 0.650725, "precision": 0.588217, "precision_weighted": 0.769621, "recall": 0.63943, "recall_weighted": 0.610448, "ap": 0.260652, "ap_weighted": 0.260652 }, { "accuracy": 0.608955, "f1": 0.551393, "f1_weighted": 0.649249, "precision": 0.577126, "precision_weighted": 0.757492, "recall": 0.621167, "recall_weighted": 0.608955, "ap": 0.250292, "ap_weighted": 0.250292 } ], "accuracy": 0.659254, "f1": 0.599813, "f1_weighted": 0.693059, "precision": 0.614301, "precision_weighted": 0.787758, "recall": 0.674675, "recall_weighted": 0.659254, "ap": 0.289149, "ap_weighted": 0.289149, "main_score": 0.659254, "hf_subset": "en", "languages": [ "eng-Latn" ] } ] }, "evaluation_time": 32.70637917518616, "kg_co2_emissions": null, "date": null }