{ "results": { "anli_r1": { "acc": 0.346, "acc_stderr": 0.01505026612756444 }, "anli_r2": { "acc": 0.338, "acc_stderr": 0.01496596071022448 }, "anli_r3": { "acc": 0.3516666666666667, "acc_stderr": 0.013789711695404789 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3115193264446996 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4707229635530771, "acc_stderr": 0.0049812201358823294, "acc_norm": 0.6292571200955985, "acc_norm_stderr": 0.004820166002253066 }, "rte": { "acc": 0.5884476534296029, "acc_stderr": 0.029621832222417196 }, "winogrande": { "acc": 0.5722178374112076, "acc_stderr": 0.013905134013839953 }, "storycloze_2016": { "acc": 0.7242116515232496, "acc_stderr": 0.010334748387645675 }, "boolq": { "acc": 0.6269113149847095, "acc_stderr": 0.008458661252058382 }, "arc_easy": { "acc": 0.6308922558922558, "acc_stderr": 0.009901987410242738, "acc_norm": 0.617003367003367, "acc_norm_stderr": 0.00997492038453648 }, "arc_challenge": { "acc": 0.2909556313993174, "acc_stderr": 0.01327307786590759, "acc_norm": 0.318259385665529, "acc_norm_stderr": 0.013611993916971453 }, "sciq": { "acc": 0.911, "acc_stderr": 0.009008893392651526, "acc_norm": 0.905, "acc_norm_stderr": 0.0092769101031033 }, "piqa": { "acc": 0.7562568008705114, "acc_stderr": 0.010017199471500617, "acc_norm": 0.766050054406964, "acc_norm_stderr": 0.00987723689513744 } }, "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 } }