{ "results": { "arc_challenge": { "acc": 0.2687713310580205, "acc_stderr": 0.012955065963710691, "acc_norm": 0.31313993174061433, "acc_norm_stderr": 0.013552671543623504 }, "arc_easy": { "acc": 0.6077441077441077, "acc_stderr": 0.010018744689650043, "acc_norm": 0.5429292929292929, "acc_norm_stderr": 0.01022189756425603 }, "boolq": { "acc": 0.6033639143730887, "acc_stderr": 0.008556148582032 }, "hellaswag": { "acc": 0.4584744074885481, "acc_stderr": 0.004972543127767873, "acc_norm": 0.6059549890460068, "acc_norm_stderr": 0.0048764594346198 }, "lambada_openai": { "ppl": 5.119857738610855, "ppl_stderr": 0.11991227443177162, "acc": 0.6357461672811954, "acc_stderr": 0.006704339729528894 }, "openbookqa": { "acc": 0.25, "acc_stderr": 0.019384310743640384, "acc_norm": 0.352, "acc_norm_stderr": 0.021380042385946048 }, "piqa": { "acc": 0.7383025027203483, "acc_stderr": 0.01025563077270823, "acc_norm": 0.7480957562568009, "acc_norm_stderr": 0.010128421335088685 }, "sciq": { "acc": 0.858, "acc_stderr": 0.011043457699378227, "acc_norm": 0.79, "acc_norm_stderr": 0.012886662332274536 }, "siqa": { "acc": 0.4083930399181167, "acc_stderr": 0.011122558066098069, "acc_norm": 0.44268167860798363, "acc_norm_stderr": 0.011239482425741961 }, "winogrande": { "acc": 0.6101026045777427, "acc_stderr": 0.013707547317008462 } }, "versions": { "arc_challenge": 0, "arc_easy": 0, "boolq": 1, "hellaswag": 0, "lambada_openai": 0, "openbookqa": 0, "piqa": 0, "sciq": 0, "siqa": 0, "winogrande": 0 }, "config": { "model": "gpt2", "model_args": "use_fast=True,pretrained=facebook/opt-2.7b,trust_remote_code=True,low_cpu_mem_usage=True,dtype=auto", "num_fewshot": 0, "batch_size": "8", "batch_sizes": [], "device": "cuda:2", "no_cache": false, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }