{ "results": { "anli_r1": { "acc": 0.339, "acc_stderr": 0.014976758771620345 }, "anli_r2": { "acc": 0.355, "acc_stderr": 0.015139491543780532 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225603 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.3383838383838384 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.475502887870942, "acc_stderr": 0.0049837889926812, "acc_norm": 0.6351324437363075, "acc_norm_stderr": 0.004804091708812568 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.02993107036293953 }, "winogrande": { "acc": 0.6006314127861089, "acc_stderr": 0.013764933546717612 }, "storycloze_2016": { "acc": 0.7354355959380011, "acc_stderr": 0.010200400541714165 }, "boolq": { "acc": 0.5620795107033639, "acc_stderr": 0.008677388652709261 }, "arc_easy": { "acc": 0.6494107744107744, "acc_stderr": 0.00979100382983156, "acc_norm": 0.6279461279461279, "acc_norm_stderr": 0.009918187193096471 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.01326157367752077, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016193 }, "sciq": { "acc": 0.921, "acc_stderr": 0.008534156773333442, "acc_norm": 0.919, "acc_norm_stderr": 0.00863212103213998 }, "piqa": { "acc": 0.7524483133841132, "acc_stderr": 0.010069703966857102, "acc_norm": 0.764417845484222, "acc_norm_stderr": 0.009901067586473885 } }, "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 } }