{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r2": { "acc": 0.34, "acc_stderr": 0.014987482264363937 }, "anli_r3": { "acc": 0.3516666666666667, "acc_stderr": 0.013789711695404803 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.3260233918128655 }, "copa": { "acc": 0.74, "acc_stderr": 0.0440844002276808 }, "hellaswag": { "acc": 0.44284007169886475, "acc_stderr": 0.004957068377516515, "acc_norm": 0.58105954989046, "acc_norm_stderr": 0.004923772581848488 }, "rte": { "acc": 0.48014440433212996, "acc_stderr": 0.0300727231673172 }, "winogrande": { "acc": 0.5548539857932123, "acc_stderr": 0.01396766295435549 }, "storycloze_2016": { "acc": 0.692143238909674, "acc_stderr": 0.010674598158758175 }, "boolq": { "acc": 0.5871559633027523, "acc_stderr": 0.008611172430472871 }, "arc_easy": { "acc": 0.5976430976430976, "acc_stderr": 0.010062244711011525, "acc_norm": 0.5585016835016835, "acc_norm_stderr": 0.010189314382749927 }, "arc_challenge": { "acc": 0.2568259385665529, "acc_stderr": 0.0127669237941168, "acc_norm": 0.295221843003413, "acc_norm_stderr": 0.013329750293382316 }, "sciq": { "acc": 0.847, "acc_stderr": 0.011389500459665532, "acc_norm": 0.809, "acc_norm_stderr": 0.012436787112179482 }, "piqa": { "acc": 0.7399347116430903, "acc_stderr": 0.0102348932490613, "acc_norm": 0.7470076169749728, "acc_norm_stderr": 0.010142888698862453 } }, "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 } }