{ "results": { "anli_r1": { "acc": 0.338, "acc_stderr": 0.014965960710224473 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.01491084616422986 }, "anli_r3": { "acc": 0.335, "acc_stderr": 0.01363087184382148 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.1940928270042194 }, "copa": { "acc": 0.63, "acc_stderr": 0.048523658709391 }, "hellaswag": { "acc": 0.29725154351722766, "acc_stderr": 0.004561141293448468, "acc_norm": 0.3256323441545509, "acc_norm_stderr": 0.004676529200753 }, "rte": { "acc": 0.5234657039711191, "acc_stderr": 0.03006330041190266 }, "winogrande": { "acc": 0.5090765588003157, "acc_stderr": 0.01405017009449771 }, "storycloze_2016": { "acc": 0.5916622127204704, "acc_stderr": 0.011366477562142522 }, "boolq": { "acc": 0.5935779816513761, "acc_stderr": 0.008590531708882188 }, "arc_easy": { "acc": 0.43434343434343436, "acc_stderr": 0.010170943451269425, "acc_norm": 0.382996632996633, "acc_norm_stderr": 0.009974920384536472 }, "arc_challenge": { "acc": 0.181740614334471, "acc_stderr": 0.011269198948880236, "acc_norm": 0.22098976109215018, "acc_norm_stderr": 0.012124929206818258 }, "sciq": { "acc": 0.736, "acc_stderr": 0.013946271849440472, "acc_norm": 0.668, "acc_norm_stderr": 0.014899597242811476 }, "piqa": { "acc": 0.6300326441784548, "acc_stderr": 0.011264415223415281, "acc_norm": 0.6322089227421109, "acc_norm_stderr": 0.011250616646678792 } }, "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 } }