{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811482 }, "anli_r2": { "acc": 0.324, "acc_stderr": 0.014806864733738857 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077247 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.36493558776167473 }, "copa": { "acc": 0.77, "acc_stderr": 0.042295258468165065 }, "hellaswag": { "acc": 0.4695279824736108, "acc_stderr": 0.004980506329407586, "acc_norm": 0.6156144194383589, "acc_norm_stderr": 0.0048545552940175395 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.5832675611681136, "acc_stderr": 0.013856250072796316 }, "storycloze_2016": { "acc": 0.7199358631747729, "acc_stderr": 0.01038376499392048 }, "boolq": { "acc": 0.6220183486238532, "acc_stderr": 0.008480656964585246 }, "arc_easy": { "acc": 0.6018518518518519, "acc_stderr": 0.010044662374653396, "acc_norm": 0.5286195286195287, "acc_norm_stderr": 0.010242962617927197 }, "arc_challenge": { "acc": 0.27474402730375425, "acc_stderr": 0.013044617212771227, "acc_norm": 0.295221843003413, "acc_norm_stderr": 0.013329750293382316 }, "sciq": { "acc": 0.832, "acc_stderr": 0.011828605831454267, "acc_norm": 0.751, "acc_norm_stderr": 0.013681600278702296 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867483, "acc_norm": 0.7600652883569097, "acc_norm_stderr": 0.009963625892809545 } }, "versions": { "anli_r1": 0, "anli_r2": 0, "anli_r3": 0, "cb": 1, "copa": 0, "hellaswag": 0, "rte": 0, "winogrande": 0, "storycloze_2016": 0, "boolq": 1, "arc_easy": 0, "arc_challenge": 0, "sciq": 0, "piqa": 0 } }