{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928369 }, "anli_r2": { "acc": 0.356, "acc_stderr": 0.015149042659306625 }, "anli_r3": { "acc": 0.3358333333333333, "acc_stderr": 0.013639261190932887 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.3196248196248196 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4556861183031269, "acc_stderr": 0.004970145708188008, "acc_norm": 0.6085441147181836, "acc_norm_stderr": 0.004870785036708275 }, "rte": { "acc": 0.4657039711191336, "acc_stderr": 0.030025579819366422 }, "winogrande": { "acc": 0.5895816890292028, "acc_stderr": 0.013825107120035868 }, "storycloze_2016": { "acc": 0.7194013896312133, "acc_stderr": 0.010389809647288821 }, "boolq": { "acc": 0.5899082568807339, "acc_stderr": 0.008602512053254416 }, "arc_easy": { "acc": 0.6372053872053872, "acc_stderr": 0.009865936757013936, "acc_norm": 0.6325757575757576, "acc_norm_stderr": 0.009892552616211551 }, "arc_challenge": { "acc": 0.2986348122866894, "acc_stderr": 0.013374078615068756, "acc_norm": 0.3310580204778157, "acc_norm_stderr": 0.013752062419817834 }, "sciq": { "acc": 0.927, "acc_stderr": 0.008230354715244054, "acc_norm": 0.934, "acc_norm_stderr": 0.007855297938697587 }, "piqa": { "acc": 0.7459194776931447, "acc_stderr": 0.010157271999135043, "acc_norm": 0.750816104461371, "acc_norm_stderr": 0.01009188277012021 } }, "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 } }