{ "results": { "copa": { "acc": 0.68, "acc_stderr": 0.046882617226215034 }, "piqa": { "acc": 0.6969532100108814, "acc_stderr": 0.010722648689531515, "acc_norm": 0.7034820457018498, "acc_norm_stderr": 0.010656078922661134 }, "prost": { "acc": 0.22694278394534587, "acc_stderr": 0.003060110855833208, "acc_norm": 0.27209649871904357, "acc_norm_stderr": 0.0032514084657504338 }, "arc_easy": { "acc": 0.5361952861952862, "acc_stderr": 0.01023286555034672, "acc_norm": 0.47895622895622897, "acc_norm_stderr": 0.01025069260202258 }, "hellaswag": { "acc": 0.3617805218084047, "acc_stderr": 0.004795337009118189, "acc_norm": 0.45797649870543716, "acc_norm_stderr": 0.004972126523031943 }, "mc_taco": { "em": 0.12912912912912913, "f1": 0.34519977153598014 }, "winogrande": { "acc": 0.5493291239147593, "acc_stderr": 0.013983928869040239 }, "wsc273": { "acc": 0.6813186813186813, "acc_stderr": 0.02825328818739863 }, "swag": { "acc": 0.4596621013695891, "acc_stderr": 0.0035235690445916223, "acc_norm": 0.6219134259722083, "acc_norm_stderr": 0.003428398656668824 }, "boolq": { "acc": 0.5856269113149847, "acc_stderr": 0.00861586377642113 }, "openbookqa": { "acc": 0.17, "acc_stderr": 0.016815633531393426, "acc_norm": 0.298, "acc_norm_stderr": 0.02047511809298897 }, "arc_challenge": { "acc": 0.2098976109215017, "acc_stderr": 0.011900548748047446, "acc_norm": 0.2431740614334471, "acc_norm_stderr": 0.012536554144587089 } }, "versions": { "copa": 0, "piqa": 0, "prost": 0, "arc_easy": 0, "hellaswag": 0, "mc_taco": 0, "winogrande": 0, "wsc273": 0, "swag": 0, "boolq": 1, "openbookqa": 0, "arc_challenge": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=facebook/xglm-1.7B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }