groundedness / eval /groundedness_eval.json
bogdanraduta's picture
Upload eval/groundedness_eval.json with huggingface_hub
d37eaca verified
Raw
History Blame Contribute Delete
5.72 kB
{
"task": "groundedness",
"threshold": 0.5,
"per_language": {
"az": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9125,
"n": 80
},
"bg": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.975,
"n": 80
},
"cs": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9615,
"n": 78
},
"da": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9625,
"n": 80
},
"de": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9359,
"n": 78
},
"el": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.95,
"n": 80
},
"en": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.8974,
"n": 78
},
"es": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.95,
"n": 80
},
"et": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9605,
"n": 76
},
"fi": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9359,
"n": 78
},
"fr": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9375,
"n": 80
},
"ga": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9744,
"n": 78
},
"hr": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9231,
"n": 78
},
"hu": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.95,
"n": 80
},
"it": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9875,
"n": 80
},
"lt": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9625,
"n": 80
},
"lv": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.95,
"n": 80
},
"mt": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9375,
"n": 80
},
"nl": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9375,
"n": 80
},
"pl": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9125,
"n": 80
},
"pt": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9625,
"n": 80
},
"ro": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 80
},
"sk": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.925,
"n": 80
},
"sl": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9625,
"n": 80
},
"sv": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9125,
"n": 80
},
"tr": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9615,
"n": 78
}
},
"per_register": {
"lexical_overlap": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.949,
"n": 412
},
"negation_conflict": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9469,
"n": 414
},
"numeric_conflict": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9084,
"n": 404
},
"scope_conflict": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9663,
"n": 416
},
"unstated": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 0.9663,
"n": 416
}
},
"per_label": {
"grounded": {
"support": 1031,
"precision": 0.9574,
"recall": 0.937,
"f1": 0.9471,
"fpr": 0.0417,
"accuracy": 0.0,
"n": 0
},
"not_grounded": {
"support": 1031,
"precision": 0.9383,
"recall": 0.9583,
"f1": 0.9482,
"fpr": 0.063,
"accuracy": 0.0,
"n": 0
}
},
"worst_languages": [
[
"en",
0.8974358974358975
],
[
"az",
0.9125
],
[
"pl",
0.9125
],
[
"sv",
0.9125
],
[
"hr",
0.9230769230769231
]
],
"pair_accuracy": 0.8991
}