model_name: step_16000 results: alias: arc_challenge_poly_bn acc: 0.20530367835757057 acc_stderr: 0.011818913259067481 acc_norm: 0.24294268605645852 acc_norm_stderr: 0.012548588352773907 alias: bangla_mmlu acc: 0.24745762711864408 acc_stderr: 0.003553322398511596 acc_norm: 0.24745762711864408 acc_norm_stderr: 0.003553322398511596 alias: boolq_bn acc: 0.5300925925925926 acc_stderr: 0.024040493481769426 acc_norm: 0.5185185185185185 acc_norm_stderr: 0.02406762825109966 alias: commonsenseqa_bn acc: 0.21048321048321048 acc_stderr: 0.011671038436522943 acc_norm: 0.2809172809172809 acc_norm_stderr: 0.012867635159173909 alias: hellaswag_poly_bn acc: 0.26823198441895696 acc_stderr: 0.004608743178348772 acc_norm: 0.291387145639472 acc_norm_stderr: 0.004726941446123244 alias: mmlu_poly_bn acc: 0.2449497014803304 acc_stderr: 0.0038894142706380414 alias: openbookqa_bn acc: 0.20724346076458752 acc_stderr: 0.018199920724686902 acc_norm: 0.20724346076458752 acc_norm_stderr: 0.018199920724686902 alias: piqa_bn acc: 0.4896626768226333 acc_stderr: 0.01166333067307569