{ "results": { "anli_r1": { "acc": 0.35, "acc_stderr": 0.015090650341444233 }, "anli_r2": { "acc": 0.331, "acc_stderr": 0.014888272588203936 }, "anli_r3": { "acc": 0.3275, "acc_stderr": 0.01355321116725194 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.33543859649122804 }, "copa": { "acc": 0.67, "acc_stderr": 0.04725815626252607 }, "hellaswag": { "acc": 0.39713204540928104, "acc_stderr": 0.004883037758919964, "acc_norm": 0.49302927703644694, "acc_norm_stderr": 0.004989296471157072 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.029931070362939533 }, "winogrande": { "acc": 0.5343330702446725, "acc_stderr": 0.014019317531542569 }, "storycloze_2016": { "acc": 0.6531266702298236, "acc_stderr": 0.011006857922124124 }, "boolq": { "acc": 0.44862385321100917, "acc_stderr": 0.008698767182005266 }, "arc_easy": { "acc": 0.4734848484848485, "acc_stderr": 0.010245347015573716, "acc_norm": 0.4612794612794613, "acc_norm_stderr": 0.010228972678389592 }, "arc_challenge": { "acc": 0.23890784982935154, "acc_stderr": 0.012461071376316621, "acc_norm": 0.26791808873720135, "acc_norm_stderr": 0.01294203019513642 }, "sciq": { "acc": 0.742, "acc_stderr": 0.013842963108656603, "acc_norm": 0.718, "acc_norm_stderr": 0.014236526215291333 }, "piqa": { "acc": 0.6806311207834603, "acc_stderr": 0.010877964076613731, "acc_norm": 0.6844396082698585, "acc_norm_stderr": 0.010843119201758936 } }, "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 } }