model_name: step_16000 results: alias: arc_challenge_poly_bn acc: 0.20444824636441403 acc_stderr: 0.011800610941743605 acc_norm: 0.2506415739948674 acc_norm_stderr: 0.01268089570605098 alias: bangla_mmlu acc: 0.2591864406779661 acc_stderr: 0.0036081062038282384 acc_norm: 0.2591864406779661 acc_norm_stderr: 0.0036081062038282384 alias: boolq_bn acc: 0.5486111111111112 acc_stderr: 0.02397005865680226 acc_norm: 0.5532407407407407 acc_norm_stderr: 0.02394722656492161 alias: commonsenseqa_bn acc: 0.26044226044226043 acc_stderr: 0.012564981568550807 acc_norm: 0.32514332514332517 acc_norm_stderr: 0.013411065386526694 alias: hellaswag_poly_bn acc: 0.27515689244752217 acc_stderr: 0.004645716668728475 acc_norm: 0.30610257520017314 acc_norm_stderr: 0.0047942606799786765 alias: mmlu_poly_bn acc: 0.26482375071562936 acc_stderr: 0.00399054308811598 alias: openbookqa_bn acc: 0.19718309859154928 acc_stderr: 0.017864968661742725 acc_norm: 0.19718309859154928 acc_norm_stderr: 0.017864968661742725 alias: piqa_bn acc: 0.49782372143634385 acc_stderr: 0.011665713661738719