{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928364 }, "anli_r2": { "acc": 0.326, "acc_stderr": 0.01483050720454104 }, "anli_r3": { "acc": 0.3433333333333333, "acc_stderr": 0.01371263383046586 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.2127316680096696 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.47400916152160927, "acc_stderr": 0.00498303542023572, "acc_norm": 0.6269667396932882, "acc_norm_stderr": 0.004826224784850451 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.02988212336311872 }, "winogrande": { "acc": 0.5864246250986582, "acc_stderr": 0.013840971763195304 }, "storycloze_2016": { "acc": 0.7167290219134153, "acc_stderr": 0.010419760409155363 }, "boolq": { "acc": 0.5825688073394495, "acc_stderr": 0.00862499005021668 }, "arc_easy": { "acc": 0.6014309764309764, "acc_stderr": 0.010046455400477937, "acc_norm": 0.531986531986532, "acc_norm_stderr": 0.010238767643185714 }, "arc_challenge": { "acc": 0.26706484641638223, "acc_stderr": 0.012928933196496354, "acc_norm": 0.28924914675767915, "acc_norm_stderr": 0.013250012579393443 }, "sciq": { "acc": 0.85, "acc_stderr": 0.011297239823409314, "acc_norm": 0.752, "acc_norm_stderr": 0.013663187134877637 }, "piqa": { "acc": 0.7551686615886833, "acc_stderr": 0.010032309105568795, "acc_norm": 0.763873775843308, "acc_norm_stderr": 0.009908965890558218 } }, "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 } }