{ "results": { "anli_r1": { "acc": 0.336, "acc_stderr": 0.014944140233795023 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.014910846164229864 }, "anli_r3": { "acc": 0.3516666666666667, "acc_stderr": 0.013789711695404785 }, "cb": { "acc": 0.2857142857142857, "acc_stderr": 0.06091449038731724, "f1": 0.24845800389121164 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.47918741286596295, "acc_stderr": 0.004985456752161002, "acc_norm": 0.6287592113124876, "acc_norm_stderr": 0.004821492994082102 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.03003973059219781 }, "winogrande": { "acc": 0.5816890292028414, "acc_stderr": 0.013863669961195904 }, "storycloze_2016": { "acc": 0.7087119187600214, "acc_stderr": 0.010506919924163614 }, "boolq": { "acc": 0.6100917431192661, "acc_stderr": 0.008530437972862622 }, "arc_easy": { "acc": 0.6018518518518519, "acc_stderr": 0.010044662374653398, "acc_norm": 0.5214646464646465, "acc_norm_stderr": 0.010250325159456652 }, "arc_challenge": { "acc": 0.27559726962457337, "acc_stderr": 0.01305716965576184, "acc_norm": 0.30631399317406144, "acc_norm_stderr": 0.013470584417276511 }, "sciq": { "acc": 0.852, "acc_stderr": 0.01123486636423524, "acc_norm": 0.768, "acc_norm_stderr": 0.01335493745228157 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.010091882770120216, "acc_norm": 0.7616974972796517, "acc_norm_stderr": 0.009940334245876219 } }, "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 } }