{ "results": { "anli_r1": { "acc": 0.325, "acc_stderr": 0.014818724459095526 }, "anli_r2": { "acc": 0.322, "acc_stderr": 0.014782913600996662 }, "anli_r3": { "acc": 0.3383333333333333, "acc_stderr": 0.013664144006618275 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3176319176319176 }, "copa": { "acc": 0.63, "acc_stderr": 0.04852365870939099 }, "hellaswag": { "acc": 0.29954192391953793, "acc_stderr": 0.004571212360565283, "acc_norm": 0.3345947022505477, "acc_norm_stderr": 0.0047088426001774385 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5217048145224941, "acc_stderr": 0.01403923921648463 }, "storycloze_2016": { "acc": 0.5889898450026724, "acc_stderr": 0.011377828319387507 }, "boolq": { "acc": 0.5382262996941896, "acc_stderr": 0.00871946009810685 }, "arc_easy": { "acc": 0.48569023569023567, "acc_stderr": 0.010255580881603624, "acc_norm": 0.4642255892255892, "acc_norm_stderr": 0.010233488709726556 }, "arc_challenge": { "acc": 0.20051194539249148, "acc_stderr": 0.011700318050499358, "acc_norm": 0.2363481228668942, "acc_norm_stderr": 0.01241496052430183 }, "sciq": { "acc": 0.844, "acc_stderr": 0.01148023500612236, "acc_norm": 0.826, "acc_norm_stderr": 0.01199449323097343 }, "piqa": { "acc": 0.6398258977149075, "acc_stderr": 0.011200375176667486, "acc_norm": 0.6436343852013058, "acc_norm_stderr": 0.011174109865864729 } }, "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 } }