| { | |
| "dataset_revision": "e8379541af4e31359cca9fbcf4b00f2671dba205", | |
| "task_name": "AmazonCounterfactualClassification", | |
| "mteb_version": "1.25.1", | |
| "scores": { | |
| "test": [ | |
| { | |
| "accuracy": 0.65997, | |
| "f1": 0.535951, | |
| "f1_weighted": 0.725304, | |
| "ap": 0.163093, | |
| "ap_weighted": 0.163093, | |
| "scores_per_experiment": [ | |
| { | |
| "accuracy": 0.644678, | |
| "f1": 0.531347, | |
| "f1_weighted": 0.713782, | |
| "ap": 0.166602, | |
| "ap_weighted": 0.166602 | |
| }, | |
| { | |
| "accuracy": 0.608696, | |
| "f1": 0.518256, | |
| "f1_weighted": 0.683489, | |
| "ap": 0.176106, | |
| "ap_weighted": 0.176106 | |
| }, | |
| { | |
| "accuracy": 0.643928, | |
| "f1": 0.529901, | |
| "f1_weighted": 0.713177, | |
| "ap": 0.164896, | |
| "ap_weighted": 0.164896 | |
| }, | |
| { | |
| "accuracy": 0.641679, | |
| "f1": 0.51983, | |
| "f1_weighted": 0.711307, | |
| "ap": 0.151661, | |
| "ap_weighted": 0.151661 | |
| }, | |
| { | |
| "accuracy": 0.668666, | |
| "f1": 0.544738, | |
| "f1_weighted": 0.732766, | |
| "ap": 0.169199, | |
| "ap_weighted": 0.169199 | |
| }, | |
| { | |
| "accuracy": 0.707646, | |
| "f1": 0.550963, | |
| "f1_weighted": 0.760934, | |
| "ap": 0.15327, | |
| "ap_weighted": 0.15327 | |
| }, | |
| { | |
| "accuracy": 0.654423, | |
| "f1": 0.525677, | |
| "f1_weighted": 0.721296, | |
| "ap": 0.151452, | |
| "ap_weighted": 0.151452 | |
| }, | |
| { | |
| "accuracy": 0.664918, | |
| "f1": 0.539092, | |
| "f1_weighted": 0.729726, | |
| "ap": 0.163361, | |
| "ap_weighted": 0.163361 | |
| }, | |
| { | |
| "accuracy": 0.696402, | |
| "f1": 0.563025, | |
| "f1_weighted": 0.754132, | |
| "ap": 0.176998, | |
| "ap_weighted": 0.176998 | |
| }, | |
| { | |
| "accuracy": 0.668666, | |
| "f1": 0.536679, | |
| "f1_weighted": 0.732435, | |
| "ap": 0.15738, | |
| "ap_weighted": 0.15738 | |
| } | |
| ], | |
| "main_score": 0.65997, | |
| "hf_subset": "en-ext", | |
| "languages": [ | |
| "eng-Latn" | |
| ] | |
| }, | |
| { | |
| "accuracy": 0.64194, | |
| "f1": 0.585969, | |
| "f1_weighted": 0.677482, | |
| "ap": 0.280748, | |
| "ap_weighted": 0.280748, | |
| "scores_per_experiment": [ | |
| { | |
| "accuracy": 0.659701, | |
| "f1": 0.606678, | |
| "f1_weighted": 0.694619, | |
| "ap": 0.299469, | |
| "ap_weighted": 0.299469 | |
| }, | |
| { | |
| "accuracy": 0.61194, | |
| "f1": 0.564082, | |
| "f1_weighted": 0.652038, | |
| "ap": 0.268001, | |
| "ap_weighted": 0.268001 | |
| }, | |
| { | |
| "accuracy": 0.592537, | |
| "f1": 0.553977, | |
| "f1_weighted": 0.633838, | |
| "ap": 0.269473, | |
| "ap_weighted": 0.269473 | |
| }, | |
| { | |
| "accuracy": 0.61194, | |
| "f1": 0.565044, | |
| "f1_weighted": 0.652016, | |
| "ap": 0.269697, | |
| "ap_weighted": 0.269697 | |
| }, | |
| { | |
| "accuracy": 0.668657, | |
| "f1": 0.603271, | |
| "f1_weighted": 0.70135, | |
| "ap": 0.285582, | |
| "ap_weighted": 0.285582 | |
| }, | |
| { | |
| "accuracy": 0.625373, | |
| "f1": 0.56863, | |
| "f1_weighted": 0.663902, | |
| "ap": 0.26389, | |
| "ap_weighted": 0.26389 | |
| }, | |
| { | |
| "accuracy": 0.744776, | |
| "f1": 0.648233, | |
| "f1_weighted": 0.760454, | |
| "ap": 0.307423, | |
| "ap_weighted": 0.307423 | |
| }, | |
| { | |
| "accuracy": 0.667164, | |
| "f1": 0.613827, | |
| "f1_weighted": 0.701223, | |
| "ap": 0.30575, | |
| "ap_weighted": 0.30575 | |
| }, | |
| { | |
| "accuracy": 0.591045, | |
| "f1": 0.547427, | |
| "f1_weighted": 0.632985, | |
| "ap": 0.259001, | |
| "ap_weighted": 0.259001 | |
| }, | |
| { | |
| "accuracy": 0.646269, | |
| "f1": 0.588519, | |
| "f1_weighted": 0.682391, | |
| "ap": 0.279194, | |
| "ap_weighted": 0.279194 | |
| } | |
| ], | |
| "main_score": 0.64194, | |
| "hf_subset": "en", | |
| "languages": [ | |
| "eng-Latn" | |
| ] | |
| } | |
| ] | |
| }, | |
| "evaluation_time": 18.05203342437744, | |
| "kg_co2_emissions": null | |
| } |