{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811488 }, "anli_r2": { "acc": 0.316, "acc_stderr": 0.014709193056057118 }, "anli_r3": { "acc": 0.3308333333333333, "acc_stderr": 0.013588208070708995 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.28154851684263454 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.4366660027882892, "acc_stderr": 0.004949589567678892, "acc_norm": 0.5635331607249552, "acc_norm_stderr": 0.0049493353568818635 }, "rte": { "acc": 0.5342960288808665, "acc_stderr": 0.030025579819366426 }, "winogrande": { "acc": 0.5808997632202052, "acc_stderr": 0.013867325192210117 }, "storycloze_2016": { "acc": 0.7151256012827365, "acc_stderr": 0.01043751398661171 }, "boolq": { "acc": 0.5703363914373089, "acc_stderr": 0.00865809540849789 }, "arc_easy": { "acc": 0.6136363636363636, "acc_stderr": 0.009991296778159617, "acc_norm": 0.5812289562289562, "acc_norm_stderr": 0.010123487160167813 }, "arc_challenge": { "acc": 0.27303754266211605, "acc_stderr": 0.013019332762635746, "acc_norm": 0.29436860068259385, "acc_norm_stderr": 0.013318528460539426 }, "sciq": { "acc": 0.88, "acc_stderr": 0.010281328012747386, "acc_norm": 0.863, "acc_norm_stderr": 0.010878848714333318 }, "piqa": { "acc": 0.7181719260065288, "acc_stderr": 0.010496675231258166, "acc_norm": 0.7132752992383025, "acc_norm_stderr": 0.01055131450310808 } }, "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 } }