8b712b12b/evaluation/rankeval/lm1-8b7-12b-results_lm-eval_global_step5494_2023-01-23-20-00-50_1shots.json

{
    "results": {
        "anli_r1": {
            "acc": 0.337,
            "acc_stderr": 0.0149550879186536
        },
        "anli_r2": {
            "acc": 0.346,
            "acc_stderr": 0.01505026612756444
        },
        "anli_r3": {
            "acc": 0.3283333333333333,
            "acc_stderr": 0.013562032919529031
        },
        "cb": {
            "acc": 0.5,
            "acc_stderr": 0.06741998624632421,
            "f1": 0.33283056812468576
        },
        "copa": {
            "acc": 0.63,
            "acc_stderr": 0.04852365870939099
        },
        "hellaswag": {
            "acc": 0.2920732921728739,
            "acc_stderr": 0.004537865171414025,
            "acc_norm": 0.3185620394343756,
            "acc_norm_stderr": 0.00464966527389065
        },
        "rte": {
            "acc": 0.5270758122743683,
            "acc_stderr": 0.0300523034631437
        },
        "winogrande": {
            "acc": 0.4988161010260458,
            "acc_stderr": 0.014052446290529019
        },
        "storycloze_2016": {
            "acc": 0.5750935328701229,
            "acc_stderr": 0.011431286492205843
        },
        "boolq": {
            "acc": 0.5113149847094801,
            "acc_stderr": 0.008742815450467041
        },
        "arc_easy": {
            "acc": 0.4595959595959596,
            "acc_stderr": 0.010226230740889025,
            "acc_norm": 0.40824915824915825,
            "acc_norm_stderr": 0.010085566195791255
        },
        "arc_challenge": {
            "acc": 0.1885665529010239,
            "acc_stderr": 0.011430897647675818,
            "acc_norm": 0.22610921501706485,
            "acc_norm_stderr": 0.012224202097063286
        },
        "sciq": {
            "acc": 0.768,
            "acc_stderr": 0.013354937452281543,
            "acc_norm": 0.734,
            "acc_norm_stderr": 0.013979965645145137
        },
        "piqa": {
            "acc": 0.6338411316648531,
            "acc_stderr": 0.011240106070308457,
            "acc_norm": 0.6381936887921654,
            "acc_norm_stderr": 0.011211397313020377
        }
    },
    "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
    }
}