evaluation_small/2b855b14bc4-results_lm-eval_global_step52452_2022-12-23-23-30-13.json

{
    "results": {
        "copa": {
            "acc": 0.71,
            "acc_stderr": 0.045604802157206845
        },
        "boolq": {
            "acc": 0.5978593272171254,
            "acc_stderr": 0.008575926383211254
        },
        "hellaswag": {
            "acc": 0.4360685122485561,
            "acc_stderr": 0.004948824501355481,
            "acc_norm": 0.5651264688309102,
            "acc_norm_stderr": 0.004947272454226218
        },
        "arc_challenge": {
            "acc": 0.257679180887372,
            "acc_stderr": 0.012780770562768409,
            "acc_norm": 0.28071672354948807,
            "acc_norm_stderr": 0.01313123812697558
        },
        "arc_easy": {
            "acc": 0.5711279461279462,
            "acc_stderr": 0.010155440652900154,
            "acc_norm": 0.5037878787878788,
            "acc_norm_stderr": 0.010259489101351842
        },
        "sciq": {
            "acc": 0.814,
            "acc_stderr": 0.012310790208412815,
            "acc_norm": 0.737,
            "acc_norm_stderr": 0.013929286594259734
        },
        "winogrande": {
            "acc": 0.5595895816890292,
            "acc_stderr": 0.013952330311915603
        },
        "piqa": {
            "acc": 0.7415669205658324,
            "acc_stderr": 0.010213971636773326,
            "acc_norm": 0.7410228509249184,
            "acc_norm_stderr": 0.010220966031405614
        },
        "rte": {
            "acc": 0.5306859205776173,
            "acc_stderr": 0.030039730592197812
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}