{ "results": { "anli_r1": { "acc": 0.314, "acc_stderr": 0.01468399195108795 }, "anli_r2": { "acc": 0.337, "acc_stderr": 0.014955087918653609 }, "anli_r3": { "acc": 0.35, "acc_stderr": 0.013774667009018558 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813057, "f1": 0.31174851513834567 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.46395140410276836, "acc_stderr": 0.004976796060456438, "acc_norm": 0.6093407687711612, "acc_norm_stderr": 0.0048690101522807505 }, "rte": { "acc": 0.592057761732852, "acc_stderr": 0.029581952519606197 }, "winogrande": { "acc": 0.5572217837411207, "acc_stderr": 0.013960157350784978 }, "storycloze_2016": { "acc": 0.7044361304115446, "acc_stderr": 0.010551778839373784 }, "boolq": { "acc": 0.617737003058104, "acc_stderr": 0.008499149690449273 }, "arc_easy": { "acc": 0.6043771043771043, "acc_stderr": 0.010033741393430983, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.010082326627832861 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.013284525292403506, "acc_norm": 0.31313993174061433, "acc_norm_stderr": 0.013552671543623494 }, "sciq": { "acc": 0.876, "acc_stderr": 0.010427498872343961, "acc_norm": 0.871, "acc_norm_stderr": 0.010605256784796565 }, "piqa": { "acc": 0.7453754080522307, "acc_stderr": 0.01016443223706049, "acc_norm": 0.7404787812840044, "acc_norm_stderr": 0.010227939888173923 } }, "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 } }