{ "results": { "anli_r1": { "acc": 0.334, "acc_stderr": 0.014922019523732963 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.014910846164229868 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077247 }, "cb": { "acc": 0.35714285714285715, "acc_stderr": 0.0646095738380922, "f1": 0.23179160021265285 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.48088030272854015, "acc_stderr": 0.004986131919673967, "acc_norm": 0.630053774148576, "acc_norm_stderr": 0.004818031396138917 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.029826764082138277 }, "winogrande": { "acc": 0.5951065509076559, "acc_stderr": 0.013795927003124939 }, "storycloze_2016": { "acc": 0.7204703367183325, "acc_stderr": 0.01037770209970486 }, "boolq": { "acc": 0.599388379204893, "acc_stderr": 0.008570545612096374 }, "arc_easy": { "acc": 0.6212121212121212, "acc_stderr": 0.009953737656542035, "acc_norm": 0.5833333333333334, "acc_norm_stderr": 0.010116282977781254 }, "arc_challenge": { "acc": 0.29266211604095566, "acc_stderr": 0.013295916103619411, "acc_norm": 0.3225255972696246, "acc_norm_stderr": 0.01365998089427737 }, "sciq": { "acc": 0.887, "acc_stderr": 0.010016552866696848, "acc_norm": 0.876, "acc_norm_stderr": 0.01042749887234396 }, "piqa": { "acc": 0.7529923830250272, "acc_stderr": 0.01006226814077262, "acc_norm": 0.7627856365614799, "acc_norm_stderr": 0.009924694933586374 } }, "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 } }