{ "results": { "hellaswag": { "acc": 0.6264688309101772, "acc_stderr": 0.00482752658488968, "acc_norm": 0.7923720374427405, "acc_norm_stderr": 0.00404779964623464 }, "copa": { "acc": 0.9, "acc_stderr": 0.030151134457776348 }, "prost": { "acc": 0.2598740392826644, "acc_stderr": 0.003204110008963041, "acc_norm": 0.2910973526900085, "acc_norm_stderr": 0.003318834364612203 }, "boolq": { "acc": 0.6840978593272171, "acc_stderr": 0.008130700051380873 }, "mc_taco": { "em": 0.11411411411411411, "f1": 0.48361974757894227 }, "winogrande": { "acc": 0.7277032359905288, "acc_stderr": 0.012510697991453936 }, "arc_challenge": { "acc": 0.46757679180887374, "acc_stderr": 0.014580637569995423, "acc_norm": 0.454778156996587, "acc_norm_stderr": 0.014551507060836352 }, "wsc273": { "acc": 0.8681318681318682, "acc_stderr": 0.020515321360773595 }, "openbookqa": { "acc": 0.294, "acc_stderr": 0.020395095484936603, "acc_norm": 0.42, "acc_norm_stderr": 0.02209471322976178 }, "swag": { "acc": 0.5861241627511746, "acc_stderr": 0.0034822550028030703, "acc_norm": 0.7036389083275018, "acc_norm_stderr": 0.0032286148364766096 }, "arc_easy": { "acc": 0.7533670033670034, "acc_stderr": 0.008844984581934908, "acc_norm": 0.5896464646464646, "acc_norm_stderr": 0.01009353125576545 }, "piqa": { "acc": 0.809575625680087, "acc_stderr": 0.009160842206469637, "acc_norm": 0.8008705114254625, "acc_norm_stderr": 0.009317391893706834 } }, "versions": { "hellaswag": 0, "copa": 0, "prost": 0, "boolq": 1, "mc_taco": 0, "winogrande": 0, "arc_challenge": 0, "wsc273": 0, "openbookqa": 0, "swag": 0, "arc_easy": 0, "piqa": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/30B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }