{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r2": { "acc": 0.331, "acc_stderr": 0.01488827258820394 }, "anli_r3": { "acc": 0.33916666666666667, "acc_stderr": 0.013672343491681808 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.1986111111111111 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.47649870543716394, "acc_stderr": 0.004984266543053125, "acc_norm": 0.6253734315873332, "acc_norm_stderr": 0.004830371317841073 }, "rte": { "acc": 0.5487364620938628, "acc_stderr": 0.029953149241808946 }, "winogrande": { "acc": 0.5753749013417522, "acc_stderr": 0.01389189315026423 }, "storycloze_2016": { "acc": 0.7226082308925709, "acc_stderr": 0.010353267472010765 }, "boolq": { "acc": 0.5501529051987768, "acc_stderr": 0.008700950643028798 }, "arc_easy": { "acc": 0.6077441077441077, "acc_stderr": 0.010018744689650043, "acc_norm": 0.539983164983165, "acc_norm_stderr": 0.010226927233491506 }, "arc_challenge": { "acc": 0.28498293515358364, "acc_stderr": 0.013191348179838793, "acc_norm": 0.30204778156996587, "acc_norm_stderr": 0.013417519144716422 }, "sciq": { "acc": 0.849, "acc_stderr": 0.011328165223341671, "acc_norm": 0.758, "acc_norm_stderr": 0.013550631705555956 }, "piqa": { "acc": 0.7519042437431991, "acc_stderr": 0.010077118315574719, "acc_norm": 0.7589771490750816, "acc_norm_stderr": 0.009979042717267314 } }, "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 } }