evaluation_small/2b855b28bc4-results_lm-eval_global_step52452_2022-12-23-13-35-31.json

{
    "results": {
        "copa": {
            "acc": 0.77,
            "acc_stderr": 0.04229525846816506
        },
        "boolq": {
            "acc": 0.5963302752293578,
            "acc_stderr": 0.008581220435616821
        },
        "hellaswag": {
            "acc": 0.4358693487353117,
            "acc_stderr": 0.004948567856373863,
            "acc_norm": 0.5608444532961562,
            "acc_norm_stderr": 0.0049526988022756385
        },
        "arc_challenge": {
            "acc": 0.24573378839590443,
            "acc_stderr": 0.012581033453730107,
            "acc_norm": 0.28242320819112626,
            "acc_norm_stderr": 0.013155456884097222
        },
        "arc_easy": {
            "acc": 0.5707070707070707,
            "acc_stderr": 0.010156678075911089,
            "acc_norm": 0.5067340067340067,
            "acc_norm_stderr": 0.010258852980991825
        },
        "sciq": {
            "acc": 0.822,
            "acc_stderr": 0.012102167676183578,
            "acc_norm": 0.732,
            "acc_norm_stderr": 0.014013292702729486
        },
        "winogrande": {
            "acc": 0.5477505919494869,
            "acc_stderr": 0.013988256216606008
        },
        "piqa": {
            "acc": 0.7383025027203483,
            "acc_stderr": 0.01025563077270823,
            "acc_norm": 0.7421109902067464,
            "acc_norm_stderr": 0.010206956662056236
        },
        "rte": {
            "acc": 0.5379061371841155,
            "acc_stderr": 0.030009848912529113
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}