evaluation_small/2b855b18bc4-results_lm-eval_global_step52452_2022-12-23-13-35-31.json

{
    "results": {
        "copa": {
            "acc": 0.75,
            "acc_stderr": 0.04351941398892446
        },
        "boolq": {
            "acc": 0.590519877675841,
            "acc_stderr": 0.008600549751320916
        },
        "hellaswag": {
            "acc": 0.43636725751842265,
            "acc_stderr": 0.004949207947265915,
            "acc_norm": 0.5636327424815774,
            "acc_norm_stderr": 0.004949207947265913
        },
        "arc_challenge": {
            "acc": 0.25,
            "acc_stderr": 0.012653835621466646,
            "acc_norm": 0.2841296928327645,
            "acc_norm_stderr": 0.013179442447653886
        },
        "arc_easy": {
            "acc": 0.5723905723905723,
            "acc_stderr": 0.010151683397430677,
            "acc_norm": 0.5067340067340067,
            "acc_norm_stderr": 0.010258852980991825
        },
        "sciq": {
            "acc": 0.812,
            "acc_stderr": 0.012361586015103754,
            "acc_norm": 0.727,
            "acc_norm_stderr": 0.014095022868717584
        },
        "winogrande": {
            "acc": 0.5509076558800315,
            "acc_stderr": 0.01397945938914085
        },
        "piqa": {
            "acc": 0.7448313384113167,
            "acc_stderr": 0.010171571592521822,
            "acc_norm": 0.7519042437431991,
            "acc_norm_stderr": 0.010077118315574706
        },
        "rte": {
            "acc": 0.5451263537906137,
            "acc_stderr": 0.029973636495415255
        }
    },
    "versions": {
        "copa": 0,
        "boolq": 1,
        "hellaswag": 0,
        "arc_challenge": 0,
        "arc_easy": 0,
        "sciq": 0,
        "winogrande": 0,
        "piqa": 0,
        "rte": 0
    }
}