{ "results": { "anli_r1": { "acc": 0.308, "acc_stderr": 0.014606483127342763 }, "anli_r2": { "acc": 0.323, "acc_stderr": 0.014794927843348639 }, "anli_r3": { "acc": 0.3441666666666667, "acc_stderr": 0.013720551062295755 }, "cb": { "acc": 0.30357142857142855, "acc_stderr": 0.06199938655510754, "f1": 0.262831508114527 }, "copa": { "acc": 0.71, "acc_stderr": 0.045604802157206845 }, "hellaswag": { "acc": 0.3874726150169289, "acc_stderr": 0.0048617741296124945, "acc_norm": 0.47759410476000796, "acc_norm_stderr": 0.004984768912326942 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317184 }, "winogrande": { "acc": 0.5564325177584846, "acc_stderr": 0.0139626949076204 }, "storycloze_2016": { "acc": 0.6515232495991449, "acc_stderr": 0.01101871778478849 }, "boolq": { "acc": 0.5577981651376147, "acc_stderr": 0.008686430526114496 }, "arc_easy": { "acc": 0.6191077441077442, "acc_stderr": 0.009964428212260372, "acc_norm": 0.5858585858585859, "acc_norm_stderr": 0.010107387673002528 }, "arc_challenge": { "acc": 0.29692832764505117, "acc_stderr": 0.013352025976725223, "acc_norm": 0.32081911262798635, "acc_norm_stderr": 0.013640943091946531 }, "sciq": { "acc": 0.833, "acc_stderr": 0.01180043432464459, "acc_norm": 0.8, "acc_norm_stderr": 0.012655439943366665 }, "piqa": { "acc": 0.7584330794341676, "acc_stderr": 0.009986718001804463, "acc_norm": 0.766050054406964, "acc_norm_stderr": 0.009877236895137432 } }, "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 } }