220m7b57b5/evaluation/lm1-220m-7b5-results_lm-eval_global_step14324_2023-01-24-13-53-29_2shots.json

{
    "results": {
        "anli_r1": {
            "acc": 0.327,
            "acc_stderr": 0.014842213153411249
        },
        "anli_r2": {
            "acc": 0.34,
            "acc_stderr": 0.014987482264363937
        },
        "anli_r3": {
            "acc": 0.3408333333333333,
            "acc_stderr": 0.013688600793296934
        },
        "cb": {
            "acc": 0.4107142857142857,
            "acc_stderr": 0.0663363415035954,
            "f1": 0.29081632653061223
        },
        "copa": {
            "acc": 0.62,
            "acc_stderr": 0.048783173121456316
        },
        "hellaswag": {
            "acc": 0.2689703246365266,
            "acc_stderr": 0.004425182676353203,
            "acc_norm": 0.27763393746265685,
            "acc_norm_stderr": 0.004469165728600334
        },
        "rte": {
            "acc": 0.4981949458483754,
            "acc_stderr": 0.030096267148976633
        },
        "winogrande": {
            "acc": 0.5201262825572218,
            "acc_stderr": 0.014041096664344329
        },
        "storycloze_2016": {
            "acc": 0.5398182789951897,
            "acc_stderr": 0.011525709570367516
        },
        "boolq": {
            "acc": 0.5908256880733945,
            "acc_stderr": 0.008599563442397349
        },
        "arc_easy": {
            "acc": 0.40404040404040403,
            "acc_stderr": 0.010069061649549545,
            "acc_norm": 0.37542087542087543,
            "acc_norm_stderr": 0.009936218527114304
        },
        "arc_challenge": {
            "acc": 0.16552901023890784,
            "acc_stderr": 0.010860860440277693,
            "acc_norm": 0.2098976109215017,
            "acc_norm_stderr": 0.011900548748047446
        },
        "sciq": {
            "acc": 0.712,
            "acc_stderr": 0.01432694179723156,
            "acc_norm": 0.689,
            "acc_norm_stderr": 0.014645596385722697
        },
        "piqa": {
            "acc": 0.5908596300326442,
            "acc_stderr": 0.011471593460443318,
            "acc_norm": 0.5859630032644179,
            "acc_norm_stderr": 0.01149211848141758
        }
    },
    "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
    }
}