evaluation/lm1-1b1-21b-c4-results_lm-eval_global_step39672_2022-12-21-12-07-40.json

{
    "results": {
        "copa": {
            "acc": 0.68,
            "acc_stderr": 0.046882617226215034
        },
        "boolq": {
            "acc": 0.5064220183486239,
            "acc_stderr": 0.00874433361394033
        },
        "hellaswag": {
            "acc": 0.3481378211511651,
            "acc_stderr": 0.004754063867700179,
            "acc_norm": 0.4282015534754033,
            "acc_norm_stderr": 0.004938068627349486
        },
        "arc_challenge": {
            "acc": 0.21245733788395904,
            "acc_stderr": 0.01195348290658295,
            "acc_norm": 0.25,
            "acc_norm_stderr": 0.012653835621466646
        },
        "arc_easy": {
            "acc": 0.48653198653198654,
            "acc_stderr": 0.010256060854840756,
            "acc_norm": 0.43813131313131315,
            "acc_norm_stderr": 0.010180937100600073
        },
        "sciq": {
            "acc": 0.758,
            "acc_stderr": 0.013550631705555946,
            "acc_norm": 0.665,
            "acc_norm_stderr": 0.014933117490932568
        },
        "winogrande": {
            "acc": 0.5153906866614049,
            "acc_stderr": 0.014045826789783666
        },
        "piqa": {
            "acc": 0.6985854189336235,
            "acc_stderr": 0.01070624824275376,
            "acc_norm": 0.705114254624592,
            "acc_norm_stderr": 0.010639030620156982
        },
        "rte": {
            "acc": 0.5306859205776173,
            "acc_stderr": 0.03003973059219781
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}