{ "results": { "anli_r1": { "acc": 0.346, "acc_stderr": 0.015050266127564448 }, "anli_r2": { "acc": 0.328, "acc_stderr": 0.01485384248727033 }, "anli_r3": { "acc": 0.3258333333333333, "acc_stderr": 0.01353542204341746 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.37160083671711575 }, "copa": { "acc": 0.71, "acc_stderr": 0.045604802157206845 }, "hellaswag": { "acc": 0.3690499900418243, "acc_stderr": 0.0048156131443854, "acc_norm": 0.4470225054769966, "acc_norm_stderr": 0.004961693567208813 }, "rte": { "acc": 0.49097472924187724, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5280189423835833, "acc_stderr": 0.014030404213405788 }, "storycloze_2016": { "acc": 0.6397648316408338, "acc_stderr": 0.011101519668493523 }, "boolq": { "acc": 0.5299694189602446, "acc_stderr": 0.0087293318183149 }, "arc_easy": { "acc": 0.5538720538720538, "acc_stderr": 0.010200057828765008, "acc_norm": 0.5336700336700336, "acc_norm_stderr": 0.010236494647406476 }, "arc_challenge": { "acc": 0.2295221843003413, "acc_stderr": 0.012288926760890788, "acc_norm": 0.2551194539249147, "acc_norm_stderr": 0.012739038695202104 }, "sciq": { "acc": 0.901, "acc_stderr": 0.009449248027662742, "acc_norm": 0.899, "acc_norm_stderr": 0.009533618929340988 }, "piqa": { "acc": 0.7040261153427638, "acc_stderr": 0.010650414317148119, "acc_norm": 0.6996735582154516, "acc_norm_stderr": 0.010695225308183143 } }, "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 } }