{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270336 }, "anli_r2": { "acc": 0.38, "acc_stderr": 0.015356947477797577 }, "anli_r3": { "acc": 0.3575, "acc_stderr": 0.013840921245257796 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3799029799029799 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.4539932284405497, "acc_stderr": 0.00496861353930925, "acc_norm": 0.6053574985062736, "acc_norm_stderr": 0.004877748536428436 }, "rte": { "acc": 0.5018050541516246, "acc_stderr": 0.030096267148976626 }, "winogrande": { "acc": 0.5832675611681136, "acc_stderr": 0.013856250072796318 }, "storycloze_2016": { "acc": 0.7204703367183325, "acc_stderr": 0.010377702099704856 }, "boolq": { "acc": 0.5596330275229358, "acc_stderr": 0.008682635667686902 }, "arc_easy": { "acc": 0.6456228956228957, "acc_stderr": 0.009815004030251743, "acc_norm": 0.6435185185185185, "acc_norm_stderr": 0.009828046544504438 }, "arc_challenge": { "acc": 0.2986348122866894, "acc_stderr": 0.013374078615068756, "acc_norm": 0.3216723549488055, "acc_norm_stderr": 0.013650488084494162 }, "sciq": { "acc": 0.921, "acc_stderr": 0.008534156773333431, "acc_norm": 0.938, "acc_norm_stderr": 0.007629823996280307 }, "piqa": { "acc": 0.7464635473340587, "acc_stderr": 0.010150090834551782, "acc_norm": 0.7529923830250272, "acc_norm_stderr": 0.010062268140772644 } }, "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 } }