{ "results": { "anli_r1": { "acc": 0.32, "acc_stderr": 0.014758652303574869 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402706 }, "anli_r3": { "acc": 0.32166666666666666, "acc_stderr": 0.013490095282989521 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.36734693877551017 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4540928101971719, "acc_stderr": 0.004968705270086761, "acc_norm": 0.6073491336387173, "acc_norm_stderr": 0.004873421833291568 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.03003973059219781 }, "winogrande": { "acc": 0.5864246250986582, "acc_stderr": 0.013840971763195308 }, "storycloze_2016": { "acc": 0.7172634954569749, "acc_stderr": 0.01041380648612127 }, "boolq": { "acc": 0.5626911314984709, "acc_stderr": 0.008676043429497423 }, "arc_easy": { "acc": 0.6388888888888888, "acc_stderr": 0.00985601342581124, "acc_norm": 0.6506734006734006, "acc_norm_stderr": 0.009782853449399295 }, "arc_challenge": { "acc": 0.30887372013651876, "acc_stderr": 0.013501770929344003, "acc_norm": 0.3395904436860068, "acc_norm_stderr": 0.013839039762820164 }, "sciq": { "acc": 0.921, "acc_stderr": 0.008534156773333438, "acc_norm": 0.933, "acc_norm_stderr": 0.007910345983177547 }, "piqa": { "acc": 0.7464635473340587, "acc_stderr": 0.010150090834551786, "acc_norm": 0.7524483133841132, "acc_norm_stderr": 0.010069703966857116 } }, "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 } }