{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r2": { "acc": 0.352, "acc_stderr": 0.015110404505648668 }, "anli_r3": { "acc": 0.34, "acc_stderr": 0.013680495725767789 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.23650793650793656 }, "copa": { "acc": 0.67, "acc_stderr": 0.04725815626252609 }, "hellaswag": { "acc": 0.3972316271659032, "acc_stderr": 0.00488324657949666, "acc_norm": 0.4969129655447122, "acc_norm_stderr": 0.004989686307484565 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317177 }, "winogrande": { "acc": 0.5059194948697711, "acc_stderr": 0.014051500838485807 }, "storycloze_2016": { "acc": 0.6515232495991449, "acc_stderr": 0.011018717784788488 }, "boolq": { "acc": 0.43241590214067277, "acc_stderr": 0.008664798701065797 }, "arc_easy": { "acc": 0.48063973063973064, "acc_stderr": 0.01025208949116552, "acc_norm": 0.46675084175084175, "acc_norm_stderr": 0.010237073872130747 }, "arc_challenge": { "acc": 0.22696245733788395, "acc_stderr": 0.01224049153613287, "acc_norm": 0.2525597269624573, "acc_norm_stderr": 0.012696728980207704 }, "sciq": { "acc": 0.746, "acc_stderr": 0.013772206565168544, "acc_norm": 0.722, "acc_norm_stderr": 0.014174516461485256 }, "piqa": { "acc": 0.690424374319913, "acc_stderr": 0.010786656752183345, "acc_norm": 0.6958650707290533, "acc_norm_stderr": 0.010733493335721314 } }, "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 } }