evaluation_old/2b855b11bc4-results_lm-eval_global_step52452_2022-12-23-13-35-31.json

{
    "results": {
        "copa": {
            "acc": 0.74,
            "acc_stderr": 0.04408440022768077
        },
        "boolq": {
            "acc": 0.5892966360856269,
            "acc_stderr": 0.008604460608471413
        },
        "hellaswag": {
            "acc": 0.43616809400517825,
            "acc_stderr": 0.004948952519517524,
            "acc_norm": 0.563931487751444,
            "acc_norm_stderr": 0.004948824501355473
        },
        "arc_challenge": {
            "acc": 0.27303754266211605,
            "acc_stderr": 0.013019332762635734,
            "acc_norm": 0.2815699658703072,
            "acc_norm_stderr": 0.013143376735009024
        },
        "arc_easy": {
            "acc": 0.5597643097643098,
            "acc_stderr": 0.010186228624515651,
            "acc_norm": 0.4978956228956229,
            "acc_norm_stderr": 0.010259692651537049
        },
        "sciq": {
            "acc": 0.802,
            "acc_stderr": 0.012607733934175315,
            "acc_norm": 0.713,
            "acc_norm_stderr": 0.014312087053809961
        },
        "winogrande": {
            "acc": 0.5485398579321231,
            "acc_stderr": 0.01398611030101776
        },
        "piqa": {
            "acc": 0.7366702937976061,
            "acc_stderr": 0.010276185322196764,
            "acc_norm": 0.7383025027203483,
            "acc_norm_stderr": 0.010255630772708227
        },
        "rte": {
            "acc": 0.5090252707581228,
            "acc_stderr": 0.030091559826331334
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}