regulated-advice / eval /regulated_advice_eval.json
bogdanraduta's picture
Upload eval/regulated_advice_eval.json with huggingface_hub
97c1855 verified
Raw
History Blame Contribute Delete
19.6 kB
{
"task": "regulated_advice",
"threshold": 0.72,
"per_language": {
"az": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9592,
"n": 49
},
"bg": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.898,
"n": 49
},
"cs": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9592,
"n": 49
},
"da": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"de": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"el": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.898,
"n": 49
},
"en": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9388,
"n": 49
},
"es": {
"support": 24,
"precision": 1.0,
"recall": 0.9583,
"f1": 0.9787,
"fpr": 0.0,
"accuracy": 0.8776,
"n": 49
},
"et": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"fi": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.8776,
"n": 49
},
"fr": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.8163,
"n": 49
},
"ga": {
"support": 24,
"precision": 1.0,
"recall": 0.9583,
"f1": 0.9787,
"fpr": 0.0,
"accuracy": 0.7143,
"n": 49
},
"hr": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.898,
"n": 49
},
"hu": {
"support": 24,
"precision": 1.0,
"recall": 0.9167,
"f1": 0.9565,
"fpr": 0.0,
"accuracy": 0.8571,
"n": 49
},
"it": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9388,
"n": 49
},
"lt": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"lv": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"mt": {
"support": 23,
"precision": 1.0,
"recall": 0.9565,
"f1": 0.9778,
"fpr": 0.0,
"accuracy": 0.875,
"n": 48
},
"nl": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.898,
"n": 49
},
"pl": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9184,
"n": 49
},
"pt": {
"support": 23,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9583,
"n": 48
},
"ro": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.9796,
"n": 49
},
"sk": {
"support": 24,
"precision": 1.0,
"recall": 0.9583,
"f1": 0.9787,
"fpr": 0.0,
"accuracy": 0.9388,
"n": 49
},
"sl": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.898,
"n": 49
},
"sv": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.8776,
"n": 49
},
"tr": {
"support": 24,
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"fpr": 0.0,
"accuracy": 0.8776,
"n": 49
}
},
"per_register": {
"definition": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 130
},
"directive": {
"support": 130,
"precision": 1.0,
"recall": 0.9846,
"f1": 0.9922,
"fpr": 0.0,
"accuracy": 0.8154,
"n": 130
},
"general_risk": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 130
},
"historical_fact": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 130
},
"hypothetical": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 130
},
"personal_recommendation": {
"support": 362,
"precision": 1.0,
"recall": 0.9972,
"f1": 0.9986,
"fpr": 0.0,
"accuracy": 0.9503,
"n": 362
},
"process_description": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0,
"accuracy": 1.0,
"n": 130
},
"suitability_claim": {
"support": 130,
"precision": 1.0,
"recall": 0.9769,
"f1": 0.9883,
"fpr": 0.0,
"accuracy": 0.3615,
"n": 130
}
},
"per_label": {
"financial_advice": {
"support": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"fpr": 0.0786,
"accuracy": 0.0,
"n": 0
},
"legal_advice": {
"support": 102,
"precision": 0.8043,
"recall": 0.7255,
"f1": 0.7629,
"fpr": 0.0154,
"accuracy": 0.0,
"n": 0
},
"medical_advice": {
"support": 520,
"precision": 0.9977,
"recall": 0.8212,
"f1": 0.9008,
"fpr": 0.0013,
"accuracy": 0.0,
"n": 0
}
},
"worst_languages": [
[
"hu",
0.9565217391304348
],
[
"mt",
0.9777777777777777
],
[
"es",
0.9787234042553191
],
[
"ga",
0.9787234042553191
],
[
"sk",
0.9787234042553191
]
],
"calibration": {
"threshold": 0.72,
"objective": "macro_f1",
"value_on_val": 0.4914,
"default_threshold": 0.5,
"default_value_on_val": 0.4888,
"improvement": 0.0026,
"chosen_on": "validation split, never test",
"curve": [
{
"threshold": 0.02,
"macro_f1": 0.4824,
"any_label_recall": 0.9945,
"any_label_fpr": 0.0
},
{
"threshold": 0.03,
"macro_f1": 0.4836,
"any_label_recall": 0.9945,
"any_label_fpr": 0.0
},
{
"threshold": 0.04,
"macro_f1": 0.4852,
"any_label_recall": 0.9945,
"any_label_fpr": 0.0
},
{
"threshold": 0.05,
"macro_f1": 0.4845,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.06,
"macro_f1": 0.4849,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.07,
"macro_f1": 0.4855,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.08,
"macro_f1": 0.486,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.09,
"macro_f1": 0.486,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.1,
"macro_f1": 0.4866,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.11,
"macro_f1": 0.4866,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.12,
"macro_f1": 0.4859,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.13,
"macro_f1": 0.4859,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.14,
"macro_f1": 0.4849,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.15,
"macro_f1": 0.4849,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.16,
"macro_f1": 0.4854,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.17,
"macro_f1": 0.4882,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.18,
"macro_f1": 0.4882,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.19,
"macro_f1": 0.4877,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.2,
"macro_f1": 0.4883,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.21,
"macro_f1": 0.486,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.22,
"macro_f1": 0.4866,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.23,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.24,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.25,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.26,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.27,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.28,
"macro_f1": 0.4871,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.29,
"macro_f1": 0.4877,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.3,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.31,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.32,
"macro_f1": 0.4861,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.33,
"macro_f1": 0.4861,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.34,
"macro_f1": 0.4861,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.35,
"macro_f1": 0.4861,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.36,
"macro_f1": 0.4861,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.37,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.38,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.39,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.4,
"macro_f1": 0.4867,
"any_label_recall": 0.9908,
"any_label_fpr": 0.0
},
{
"threshold": 0.41,
"macro_f1": 0.4873,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.42,
"macro_f1": 0.4873,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.43,
"macro_f1": 0.4873,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.44,
"macro_f1": 0.4873,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.45,
"macro_f1": 0.4885,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.46,
"macro_f1": 0.4885,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.47,
"macro_f1": 0.4885,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.48,
"macro_f1": 0.4885,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.49,
"macro_f1": 0.4885,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.5,
"macro_f1": 0.4888,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.51,
"macro_f1": 0.4894,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.52,
"macro_f1": 0.4894,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.53,
"macro_f1": 0.49,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.54,
"macro_f1": 0.4895,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.55,
"macro_f1": 0.4895,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.56,
"macro_f1": 0.4895,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.57,
"macro_f1": 0.4895,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.58,
"macro_f1": 0.4901,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.59,
"macro_f1": 0.4901,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.6,
"macro_f1": 0.4907,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.61,
"macro_f1": 0.4907,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.62,
"macro_f1": 0.4907,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.63,
"macro_f1": 0.4907,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.64,
"macro_f1": 0.4907,
"any_label_recall": 0.989,
"any_label_fpr": 0.0
},
{
"threshold": 0.65,
"macro_f1": 0.4908,
"any_label_recall": 0.9872,
"any_label_fpr": 0.0
},
{
"threshold": 0.66,
"macro_f1": 0.4908,
"any_label_recall": 0.9872,
"any_label_fpr": 0.0
},
{
"threshold": 0.67,
"macro_f1": 0.4901,
"any_label_recall": 0.9872,
"any_label_fpr": 0.0
},
{
"threshold": 0.68,
"macro_f1": 0.4907,
"any_label_recall": 0.9853,
"any_label_fpr": 0.0
},
{
"threshold": 0.69,
"macro_f1": 0.4913,
"any_label_recall": 0.9835,
"any_label_fpr": 0.0
},
{
"threshold": 0.7,
"macro_f1": 0.4913,
"any_label_recall": 0.9835,
"any_label_fpr": 0.0
},
{
"threshold": 0.71,
"macro_f1": 0.4913,
"any_label_recall": 0.9835,
"any_label_fpr": 0.0
},
{
"threshold": 0.72,
"macro_f1": 0.4914,
"any_label_recall": 0.9817,
"any_label_fpr": 0.0
},
{
"threshold": 0.73,
"macro_f1": 0.4909,
"any_label_recall": 0.9799,
"any_label_fpr": 0.0
},
{
"threshold": 0.74,
"macro_f1": 0.4909,
"any_label_recall": 0.9799,
"any_label_fpr": 0.0
},
{
"threshold": 0.75,
"macro_f1": 0.4909,
"any_label_recall": 0.978,
"any_label_fpr": 0.0
},
{
"threshold": 0.76,
"macro_f1": 0.4909,
"any_label_recall": 0.978,
"any_label_fpr": 0.0
},
{
"threshold": 0.77,
"macro_f1": 0.4909,
"any_label_recall": 0.978,
"any_label_fpr": 0.0
},
{
"threshold": 0.78,
"macro_f1": 0.4909,
"any_label_recall": 0.978,
"any_label_fpr": 0.0
},
{
"threshold": 0.79,
"macro_f1": 0.4899,
"any_label_recall": 0.9762,
"any_label_fpr": 0.0
},
{
"threshold": 0.8,
"macro_f1": 0.4893,
"any_label_recall": 0.9762,
"any_label_fpr": 0.0
},
{
"threshold": 0.81,
"macro_f1": 0.4888,
"any_label_recall": 0.9707,
"any_label_fpr": 0.0
},
{
"threshold": 0.82,
"macro_f1": 0.4882,
"any_label_recall": 0.9689,
"any_label_fpr": 0.0
},
{
"threshold": 0.83,
"macro_f1": 0.488,
"any_label_recall": 0.9652,
"any_label_fpr": 0.0
},
{
"threshold": 0.84,
"macro_f1": 0.488,
"any_label_recall": 0.9652,
"any_label_fpr": 0.0
},
{
"threshold": 0.85,
"macro_f1": 0.488,
"any_label_recall": 0.9652,
"any_label_fpr": 0.0
},
{
"threshold": 0.86,
"macro_f1": 0.4875,
"any_label_recall": 0.9634,
"any_label_fpr": 0.0
},
{
"threshold": 0.87,
"macro_f1": 0.4887,
"any_label_recall": 0.9597,
"any_label_fpr": 0.0
},
{
"threshold": 0.88,
"macro_f1": 0.4887,
"any_label_recall": 0.9597,
"any_label_fpr": 0.0
},
{
"threshold": 0.89,
"macro_f1": 0.4887,
"any_label_recall": 0.9597,
"any_label_fpr": 0.0
},
{
"threshold": 0.9,
"macro_f1": 0.4887,
"any_label_recall": 0.9597,
"any_label_fpr": 0.0
},
{
"threshold": 0.91,
"macro_f1": 0.4882,
"any_label_recall": 0.9579,
"any_label_fpr": 0.0
},
{
"threshold": 0.92,
"macro_f1": 0.4873,
"any_label_recall": 0.9505,
"any_label_fpr": 0.0
},
{
"threshold": 0.93,
"macro_f1": 0.4874,
"any_label_recall": 0.9469,
"any_label_fpr": 0.0
},
{
"threshold": 0.94,
"macro_f1": 0.4861,
"any_label_recall": 0.9451,
"any_label_fpr": 0.0
},
{
"threshold": 0.95,
"macro_f1": 0.4863,
"any_label_recall": 0.9377,
"any_label_fpr": 0.0
}
],
"notes": []
},
"pair_accuracy": 0.7973
}