{ "results": { "anli_r1": { "acc": 0.31, "acc_stderr": 0.0146326386586329 }, "anli_r2": { "acc": 0.335, "acc_stderr": 0.014933117490932573 }, "anli_r3": { "acc": 0.30916666666666665, "acc_stderr": 0.013346684134591945 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2349033816425121 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542127 }, "hellaswag": { "acc": 0.45289782911770565, "acc_stderr": 0.004967591267557399, "acc_norm": 0.5914160525791675, "acc_norm_stderr": 0.00490567440861401 }, "rte": { "acc": 0.47653429602888087, "acc_stderr": 0.030063300411902652 }, "winogrande": { "acc": 0.5619573796369376, "acc_stderr": 0.013944181296470804 }, "storycloze_2016": { "acc": 0.692143238909674, "acc_stderr": 0.010674598158758175 }, "boolq": { "acc": 0.5896024464831804, "acc_stderr": 0.008603488048617523 }, "arc_easy": { "acc": 0.6001683501683501, "acc_stderr": 0.010051788039412923, "acc_norm": 0.5698653198653199, "acc_norm_stderr": 0.010159130445178514 }, "arc_challenge": { "acc": 0.2790102389078498, "acc_stderr": 0.013106784883601333, "acc_norm": 0.2901023890784983, "acc_norm_stderr": 0.013261573677520766 }, "sciq": { "acc": 0.887, "acc_stderr": 0.01001655286669685, "acc_norm": 0.852, "acc_norm_stderr": 0.01123486636423527 }, "piqa": { "acc": 0.7404787812840044, "acc_stderr": 0.010227939888173922, "acc_norm": 0.7437431991294886, "acc_norm_stderr": 0.010185787831565055 } }, "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 } }