{ "results": { "anli_r1": { "acc": 0.333, "acc_stderr": 0.014910846164229868 }, "anli_r2": { "acc": 0.336, "acc_stderr": 0.014944140233795027 }, "anli_r3": { "acc": 0.3433333333333333, "acc_stderr": 0.01371263383046586 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.21956970232832299 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4629555865365465, "acc_stderr": 0.0049760677264325615, "acc_norm": 0.6056562437761402, "acc_norm_stderr": 0.004877104939356237 }, "rte": { "acc": 0.5848375451263538, "acc_stderr": 0.02966006629089349 }, "winogrande": { "acc": 0.5832675611681136, "acc_stderr": 0.01385625007279632 }, "storycloze_2016": { "acc": 0.7097808658471406, "acc_stderr": 0.010495529690730063 }, "boolq": { "acc": 0.617737003058104, "acc_stderr": 0.008499149690449282 }, "arc_easy": { "acc": 0.569023569023569, "acc_stderr": 0.010161552863493758, "acc_norm": 0.5071548821548821, "acc_norm_stderr": 0.01025873302244637 }, "arc_challenge": { "acc": 0.2619453924914676, "acc_stderr": 0.012849054826858114, "acc_norm": 0.295221843003413, "acc_norm_stderr": 0.01332975029338232 }, "sciq": { "acc": 0.83, "acc_stderr": 0.01188449583454167, "acc_norm": 0.734, "acc_norm_stderr": 0.013979965645145158 }, "piqa": { "acc": 0.7442872687704026, "acc_stderr": 0.010178690109459857, "acc_norm": 0.7475516866158868, "acc_norm_stderr": 0.010135665547362354 } }, "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 } }