Adaptive-Repetition-Controller-ARC / hedging_results.json
LoganResearch's picture
Upload folder using huggingface_hub
63b640e verified
[
{
"step": 3000,
"accuracy": 0.7798140048980713,
"precision": 0.06394045212277155,
"recall": 0.6678825110385871,
"f1": 0.11670776094869087,
"pos_risk": 0.524723470211029,
"neg_risk": 0.4489431381225586,
"separation": 1.1687971719656465
},
{
"step": 4000,
"accuracy": 0.8607996106147766,
"precision": 0.08731814842027921,
"recall": 0.5703589940487618,
"f1": 0.15145027272263856,
"pos_risk": 0.5151649713516235,
"neg_risk": 0.4292229413986206,
"separation": 1.2002270187911235
},
{
"step": 5000,
"accuracy": 0.8619410991668701,
"precision": 0.09372991293168936,
"recall": 0.6158571702822039,
"f1": 0.1626981108152656,
"pos_risk": 0.5229318737983704,
"neg_risk": 0.42363420128822327,
"separation": 1.234394843967258
},
{
"step": 6000,
"accuracy": 0.873987078666687,
"precision": 0.10097000352146493,
"recall": 0.6054904972163563,
"f1": 0.17307797837897163,
"pos_risk": 0.5275717377662659,
"neg_risk": 0.4137572944164276,
"separation": 1.2750753760374536
},
{
"step": 7000,
"accuracy": 0.9015830159187317,
"precision": 0.12172369670202667,
"recall": 0.5661355346515646,
"f1": 0.20036689767631471,
"pos_risk": 0.521373987197876,
"neg_risk": 0.3951682150363922,
"separation": 1.319372275803764
},
{
"step": 8000,
"accuracy": 0.8688943982124329,
"precision": 0.09942703067071115,
"recall": 0.6229602610865809,
"f1": 0.1714844369286054,
"pos_risk": 0.5516535639762878,
"neg_risk": 0.40235474705696106,
"separation": 1.3710626456165327
},
{
"step": 9000,
"accuracy": 0.8865934014320374,
"precision": 0.11200424929178471,
"recall": 0.6072182760606643,
"f1": 0.18912374062004847,
"pos_risk": 0.5500459671020508,
"neg_risk": 0.3843628168106079,
"separation": 1.4310592571525516
},
{
"step": 10000,
"accuracy": 0.8839634656906128,
"precision": 0.11537280327589149,
"recall": 0.6490689191783452,
"f1": 0.19592049603059628,
"pos_risk": 0.5594488978385925,
"neg_risk": 0.37506988644599915,
"separation": 1.491585749897678
}
]