{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.01487687202745673 }, "anli_r2": { "acc": 0.318, "acc_stderr": 0.0147340793093119 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077247 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.3333333333333333 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932262 }, "hellaswag": { "acc": 0.46853216490738897, "acc_stderr": 0.004979889597551665, "acc_norm": 0.6188010356502689, "acc_norm_stderr": 0.004846886929763445 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.02993107036293953 }, "winogrande": { "acc": 0.580110497237569, "acc_stderr": 0.013870943986310391 }, "storycloze_2016": { "acc": 0.7145911277391769, "acc_stderr": 0.010443395884062115 }, "boolq": { "acc": 0.6214067278287462, "acc_stderr": 0.00848334171802448 }, "arc_easy": { "acc": 0.6077441077441077, "acc_stderr": 0.010018744689650043, "acc_norm": 0.5702861952861953, "acc_norm_stderr": 0.010157908005763674 }, "arc_challenge": { "acc": 0.29436860068259385, "acc_stderr": 0.013318528460539426, "acc_norm": 0.31569965870307165, "acc_norm_stderr": 0.013582571095815291 }, "sciq": { "acc": 0.887, "acc_stderr": 0.010016552866696855, "acc_norm": 0.856, "acc_norm_stderr": 0.01110798754893915 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867483, "acc_norm": 0.7573449401523396, "acc_norm_stderr": 0.010002002569708688 } }, "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 } }