{ "results": { "anli_r1": { "acc": 0.344, "acc_stderr": 0.015029633724408945 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928355 }, "anli_r3": { "acc": 0.35583333333333333, "acc_stderr": 0.013826518748493322 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.3235431235431235 }, "copa": { "acc": 0.62, "acc_stderr": 0.048783173121456316 }, "hellaswag": { "acc": 0.2658832901812388, "acc_stderr": 0.0044089948686501, "acc_norm": 0.26558454491137223, "acc_norm_stderr": 0.004407413723383407 }, "rte": { "acc": 0.5523465703971119, "acc_stderr": 0.02993107036293953 }, "winogrande": { "acc": 0.5011838989739542, "acc_stderr": 0.014052446290529015 }, "storycloze_2016": { "acc": 0.5227151256012827, "acc_stderr": 0.011550494192008948 }, "boolq": { "acc": 0.6128440366972477, "acc_stderr": 0.008519429207594412 }, "arc_easy": { "acc": 0.3421717171717172, "acc_stderr": 0.009735236771958743, "acc_norm": 0.32365319865319864, "acc_norm_stderr": 0.009600478182273768 }, "arc_challenge": { "acc": 0.16467576791808874, "acc_stderr": 0.010838369209479231, "acc_norm": 0.20733788395904437, "acc_norm_stderr": 0.011846905782971364 }, "sciq": { "acc": 0.556, "acc_stderr": 0.01571976816340209, "acc_norm": 0.541, "acc_norm_stderr": 0.015766025737882165 }, "piqa": { "acc": 0.5669205658324266, "acc_stderr": 0.01156086442315138, "acc_norm": 0.5571273122959739, "acc_norm_stderr": 0.011589430503509102 } }, "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 } }