{ "results": { "anli_r1": { "acc": 0.34, "acc_stderr": 0.014987482264363937 }, "anli_r2": { "acc": 0.326, "acc_stderr": 0.014830507204541033 }, "anli_r3": { "acc": 0.3458333333333333, "acc_stderr": 0.013736245342311014 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644648, "f1": 0.33534439416792355 }, "copa": { "acc": 0.73, "acc_stderr": 0.044619604333847394 }, "hellaswag": { "acc": 0.45030870344552876, "acc_stderr": 0.0049650784774355715, "acc_norm": 0.60017924716192, "acc_norm_stderr": 0.004888601874547486 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5674822415153907, "acc_stderr": 0.013923911578623827 }, "storycloze_2016": { "acc": 0.7012292891501871, "acc_stderr": 0.010584692134739974 }, "boolq": { "acc": 0.5801223241590214, "acc_stderr": 0.008632045504781744 }, "arc_easy": { "acc": 0.6426767676767676, "acc_stderr": 0.009833205612463114, "acc_norm": 0.6426767676767676, "acc_norm_stderr": 0.009833205612463106 }, "arc_challenge": { "acc": 0.3165529010238908, "acc_stderr": 0.01359243151906808, "acc_norm": 0.3370307167235495, "acc_norm_stderr": 0.013813476652902274 }, "sciq": { "acc": 0.932, "acc_stderr": 0.007964887911291603, "acc_norm": 0.929, "acc_norm_stderr": 0.008125578442487914 }, "piqa": { "acc": 0.7584330794341676, "acc_stderr": 0.009986718001804461, "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 } }