8b712b12b/evaluation/rankeval/lm1-8b7-12b-results_lm-eval_global_step5494_2023-01-25-13-37-24_0shots.json

{
    "results": {
        "anli_r1": {
            "acc": 0.338,
            "acc_stderr": 0.014965960710224479
        },
        "anli_r2": {
            "acc": 0.337,
            "acc_stderr": 0.014955087918653605
        },
        "anli_r3": {
            "acc": 0.33916666666666667,
            "acc_stderr": 0.013672343491681815
        },
        "cb": {
            "acc": 0.4107142857142857,
            "acc_stderr": 0.0663363415035954,
            "f1": 0.1940928270042194
        },
        "copa": {
            "acc": 0.65,
            "acc_stderr": 0.0479372485441102
        },
        "hellaswag": {
            "acc": 0.2916749651463852,
            "acc_stderr": 0.004536045368404717,
            "acc_norm": 0.3174666401115316,
            "acc_norm_stderr": 0.004645393477680678
        },
        "rte": {
            "acc": 0.5379061371841155,
            "acc_stderr": 0.03000984891252912
        },
        "winogrande": {
            "acc": 0.4940805051302289,
            "acc_stderr": 0.014051500838485807
        },
        "storycloze_2016": {
            "acc": 0.5911277391769107,
            "acc_stderr": 0.011368775493925617
        },
        "boolq": {
            "acc": 0.5403669724770642,
            "acc_stderr": 0.008716508381476019
        },
        "arc_easy": {
            "acc": 0.45707070707070707,
            "acc_stderr": 0.01022189756425604,
            "acc_norm": 0.39941077441077444,
            "acc_norm_stderr": 0.010050018228742113
        },
        "arc_challenge": {
            "acc": 0.19368600682593856,
            "acc_stderr": 0.01154842540997854,
            "acc_norm": 0.23976109215017063,
            "acc_norm_stderr": 0.012476304127453947
        },
        "sciq": {
            "acc": 0.757,
            "acc_stderr": 0.01356964019917743,
            "acc_norm": 0.675,
            "acc_norm_stderr": 0.014818724459095526
        },
        "piqa": {
            "acc": 0.6381936887921654,
            "acc_stderr": 0.011211397313020373,
            "acc_norm": 0.6349292709466812,
            "acc_norm_stderr": 0.011233021830554834
        }
    },
    "versions": {
        "anli_r1": 0,
        "anli_r2": 0,
        "anli_r3": 0,
        "cb": 1,
        "copa": 0,
        "hellaswag": 0,
        "rte": 0,
        "winogrande": 0,
        "storycloze_2016": 0,
        "boolq": 1,
        "arc_easy": 0,
        "arc_challenge": 0,
        "sciq": 0,
        "piqa": 0
    }
}