{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r2": { "acc": 0.316, "acc_stderr": 0.01470919305605713 }, "anli_r3": { "acc": 0.3591666666666667, "acc_stderr": 0.013855141559780364 }, "cb": { "acc": 0.26785714285714285, "acc_stderr": 0.05971290310957635, "f1": 0.21294539321104786 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.5201155148376817, "acc_stderr": 0.004985741706385719, "acc_norm": 0.6825333598884684, "acc_norm_stderr": 0.004645393477680675 }, "rte": { "acc": 0.4657039711191336, "acc_stderr": 0.030025579819366426 }, "winogrande": { "acc": 0.5872138910812944, "acc_stderr": 0.013837060648682103 }, "storycloze_2016": { "acc": 0.7365045430251203, "acc_stderr": 0.010187168219156485 }, "boolq": { "acc": 0.6477064220183486, "acc_stderr": 0.00835476049390613 }, "arc_easy": { "acc": 0.6422558922558923, "acc_stderr": 0.009835772757343361, "acc_norm": 0.6035353535353535, "acc_norm_stderr": 0.010037412763064529 }, "arc_challenge": { "acc": 0.3054607508532423, "acc_stderr": 0.0134600804780025, "acc_norm": 0.3319112627986348, "acc_norm_stderr": 0.013760988200880538 }, "sciq": { "acc": 0.905, "acc_stderr": 0.009276910103103329, "acc_norm": 0.88, "acc_norm_stderr": 0.0102813280127474 }, "piqa": { "acc": 0.764961915125136, "acc_stderr": 0.009893146688805326, "acc_norm": 0.7725788900979326, "acc_norm_stderr": 0.009779850767847232 } }, "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 } }