evaluation/1b121b4bc4-results_lm-eval_global_step39672_2022-12-22-07-35-31.json

{
    "results": {
        "copa": {
            "acc": 0.67,
            "acc_stderr": 0.04725815626252607
        },
        "boolq": {
            "acc": 0.5788990825688073,
            "acc_stderr": 0.008635491562221343
        },
        "hellaswag": {
            "acc": 0.3541127265484963,
            "acc_stderr": 0.00477266165962884,
            "acc_norm": 0.43089026090420235,
            "acc_norm_stderr": 0.004941887610849026
        },
        "arc_challenge": {
            "acc": 0.21160409556313994,
            "acc_stderr": 0.011935916358632859,
            "acc_norm": 0.2551194539249147,
            "acc_norm_stderr": 0.012739038695202105
        },
        "arc_easy": {
            "acc": 0.49242424242424243,
            "acc_stderr": 0.01025860579215332,
            "acc_norm": 0.4318181818181818,
            "acc_norm_stderr": 0.010163945352271709
        },
        "sciq": {
            "acc": 0.75,
            "acc_stderr": 0.013699915608779773,
            "acc_norm": 0.654,
            "acc_norm_stderr": 0.015050266127564448
        },
        "winogrande": {
            "acc": 0.505130228887135,
            "acc_stderr": 0.01405174596179052
        },
        "piqa": {
            "acc": 0.6991294885745375,
            "acc_stderr": 0.010700745724145973,
            "acc_norm": 0.7002176278563657,
            "acc_norm_stderr": 0.010689686967138092
        },
        "rte": {
            "acc": 0.5379061371841155,
            "acc_stderr": 0.030009848912529117
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}