8b712b12b/evaluation/rankeval/lm1-8b7-12b-results_lm-eval_global_step5494_2023-01-24-13-57-43_4shots.json

{
    "results": {
        "anli_r1": {
            "acc": 0.351,
            "acc_stderr": 0.015100563798316407
        },
        "anli_r2": {
            "acc": 0.357,
            "acc_stderr": 0.015158521721486774
        },
        "anli_r3": {
            "acc": 0.3433333333333333,
            "acc_stderr": 0.01371263383046586
        },
        "cb": {
            "acc": 0.42857142857142855,
            "acc_stderr": 0.06672848092813058,
            "f1": 0.27903469079939663
        },
        "copa": {
            "acc": 0.66,
            "acc_stderr": 0.04760952285695237
        },
        "hellaswag": {
            "acc": 0.2913762198765186,
            "acc_stderr": 0.0045346777501027325,
            "acc_norm": 0.3185620394343756,
            "acc_norm_stderr": 0.004649665273890652
        },
        "rte": {
            "acc": 0.47653429602888087,
            "acc_stderr": 0.03006330041190266
        },
        "winogrande": {
            "acc": 0.49171270718232046,
            "acc_stderr": 0.014050555322824194
        },
        "storycloze_2016": {
            "acc": 0.5702832709780866,
            "acc_stderr": 0.011447631560863357
        },
        "boolq": {
            "acc": 0.5119266055045871,
            "acc_stderr": 0.008742566760633423
        },
        "arc_easy": {
            "acc": 0.45707070707070707,
            "acc_stderr": 0.010221897564256047,
            "acc_norm": 0.42424242424242425,
            "acc_norm_stderr": 0.010141333654958574
        },
        "arc_challenge": {
            "acc": 0.1962457337883959,
            "acc_stderr": 0.011606019881416288,
            "acc_norm": 0.23208191126279865,
            "acc_norm_stderr": 0.012336718284948854
        },
        "sciq": {
            "acc": 0.785,
            "acc_stderr": 0.01299784381903181,
            "acc_norm": 0.769,
            "acc_norm_stderr": 0.013334797216936433
        },
        "piqa": {
            "acc": 0.6398258977149075,
            "acc_stderr": 0.011200375176667474,
            "acc_norm": 0.6294885745375408,
            "acc_norm_stderr": 0.011267826475447662
        }
    },
    "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
    }
}