3b977b77b/evaluation/lm1-3b9-77b-results_lm-eval_global_step73814_2022-12-03-12-23-46.json

{
    "results": {
        "boolq": {
            "acc": 0.5859327217125382,
            "acc_stderr": 0.008614932353134947
        },
        "hellaswag": {
            "acc": 0.40689105755825533,
            "acc_stderr": 0.004902502514738602,
            "acc_norm": 0.5210117506472814,
            "acc_norm_stderr": 0.0049853735507751065
        },
        "arc_challenge": {
            "acc": 0.26535836177474403,
            "acc_stderr": 0.012902554762313967,
            "acc_norm": 0.295221843003413,
            "acc_norm_stderr": 0.013329750293382316
        },
        "arc_easy": {
            "acc": 0.5896464646464646,
            "acc_stderr": 0.010093531255765457,
            "acc_norm": 0.5404040404040404,
            "acc_norm_stderr": 0.010226230740889027
        },
        "sciq": {
            "acc": 0.851,
            "acc_stderr": 0.011266140684632175,
            "acc_norm": 0.795,
            "acc_norm_stderr": 0.012772554096113132
        }
    },
    "versions": {
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0
    }
}