{ "results": { "anli_r1": { "acc": 0.36, "acc_stderr": 0.015186527932040117 }, "anli_r2": { "acc": 0.347, "acc_stderr": 0.015060472031706625 }, "anli_r3": { "acc": 0.3625, "acc_stderr": 0.01388303787422552 }, "cb": { "acc": 0.5535714285714286, "acc_stderr": 0.06703189227942395, "f1": 0.4538378958668814 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.45180242979486157, "acc_stderr": 0.004966544724452227, "acc_norm": 0.5955984863572994, "acc_norm_stderr": 0.004897728370737246 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5706393054459353, "acc_stderr": 0.013911537499969163 }, "storycloze_2016": { "acc": 0.7177979690005345, "acc_stderr": 0.010407834479647672 }, "boolq": { "acc": 0.545565749235474, "acc_stderr": 0.008708665643758015 }, "arc_easy": { "acc": 0.640993265993266, "acc_stderr": 0.009843424713072174, "acc_norm": 0.6186868686868687, "acc_norm_stderr": 0.009966542497171025 }, "arc_challenge": { "acc": 0.302901023890785, "acc_stderr": 0.013428241573185349, "acc_norm": 0.32337883959044367, "acc_norm_stderr": 0.013669421630012129 }, "sciq": { "acc": 0.915, "acc_stderr": 0.008823426366942331, "acc_norm": 0.912, "acc_norm_stderr": 0.008963053962592085 }, "piqa": { "acc": 0.7578890097932536, "acc_stderr": 0.009994371269104385, "acc_norm": 0.7752992383025027, "acc_norm_stderr": 0.009738282586548389 } }, "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 } }