evaluation/1b121b10bc4-results_lm-eval_global_step39672_2022-12-22-07-35-19.json

{
    "results": {
        "copa": {
            "acc": 0.72,
            "acc_stderr": 0.04512608598542127
        },
        "boolq": {
            "acc": 0.5235474006116208,
            "acc_stderr": 0.008735351675636605
        },
        "hellaswag": {
            "acc": 0.3556064528978291,
            "acc_stderr": 0.0047771835089498215,
            "acc_norm": 0.4304919338777136,
            "acc_norm_stderr": 0.004941331215598556
        },
        "arc_challenge": {
            "acc": 0.2175767918088737,
            "acc_stderr": 0.012057262020972504,
            "acc_norm": 0.2551194539249147,
            "acc_norm_stderr": 0.012739038695202104
        },
        "arc_easy": {
            "acc": 0.49242424242424243,
            "acc_stderr": 0.010258605792153321,
            "acc_norm": 0.43897306397306396,
            "acc_norm_stderr": 0.010183076012972067
        },
        "sciq": {
            "acc": 0.754,
            "acc_stderr": 0.013626065817750638,
            "acc_norm": 0.666,
            "acc_norm_stderr": 0.01492201952373297
        },
        "winogrande": {
            "acc": 0.5288082083662194,
            "acc_stderr": 0.014029141615909615
        },
        "piqa": {
            "acc": 0.70620239390642,
            "acc_stderr": 0.010627574080514797,
            "acc_norm": 0.7013057671381937,
            "acc_norm_stderr": 0.010678556398149226
        },
        "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
    }
}