{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r2": { "acc": 0.348, "acc_stderr": 0.01507060460376841 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.013759437498874072 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.32619912953739855 }, "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036844 }, "hellaswag": { "acc": 0.4765982871937861, "acc_stderr": 0.004984313205791442, "acc_norm": 0.6382194781915953, "acc_norm_stderr": 0.00479533700911818 }, "rte": { "acc": 0.5740072202166066, "acc_stderr": 0.02976495674177765 }, "winogrande": { "acc": 0.6022099447513812, "acc_stderr": 0.013755743513749027 }, "storycloze_2016": { "acc": 0.726349545697488, "acc_stderr": 0.010309797094497109 }, "boolq": { "acc": 0.5776758409785933, "acc_stderr": 0.008638883260317736 }, "arc_easy": { "acc": 0.6464646464646465, "acc_stderr": 0.009809728948151492, "acc_norm": 0.6317340067340067, "acc_norm_stderr": 0.009897286209010888 }, "arc_challenge": { "acc": 0.28924914675767915, "acc_stderr": 0.013250012579393443, "acc_norm": 0.3242320819112628, "acc_norm_stderr": 0.013678810399518815 }, "sciq": { "acc": 0.925, "acc_stderr": 0.00833333333333336, "acc_norm": 0.921, "acc_norm_stderr": 0.008534156773333443 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867486, "acc_norm": 0.7611534276387377, "acc_norm_stderr": 0.009948120385337484 } }, "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 } }