{ "results": { "arc_challenge": { "acc": 0.30716723549488056, "acc_stderr": 0.013481034054980945, "acc_norm": 0.34812286689419797, "acc_norm_stderr": 0.013921008595179338 }, "arc_easy": { "acc": 0.6565656565656566, "acc_stderr": 0.00974381736896, "acc_norm": 0.6014309764309764, "acc_norm_stderr": 0.010046455400477947 }, "boolq": { "acc": 0.6602446483180429, "acc_stderr": 0.00828377201314756 }, "hellaswag": { "acc": 0.5051782513443537, "acc_stderr": 0.004989513809408587, "acc_norm": 0.6719776936865166, "acc_norm_stderr": 0.004685334844038652 }, "lambada_openai": { "ppl": 4.252533670173101, "ppl_stderr": 0.0927155022353668, "acc": 0.6764991267222977, "acc_stderr": 0.006517535744360227 }, "openbookqa": { "acc": 0.276, "acc_stderr": 0.020011219298073524, "acc_norm": 0.372, "acc_norm_stderr": 0.0216371979857224 }, "piqa": { "acc": 0.7633297062023939, "acc_stderr": 0.009916841655042804, "acc_norm": 0.766050054406964, "acc_norm_stderr": 0.009877236895137437 }, "sciq": { "acc": 0.901, "acc_stderr": 0.009449248027662761, "acc_norm": 0.853, "acc_norm_stderr": 0.011203415395160333 }, "siqa": { "acc": 0.4263050153531218, "acc_stderr": 0.011190503463264742, "acc_norm": 0.4595701125895599, "acc_norm_stderr": 0.011277022486079959 }, "winogrande": { "acc": 0.6535122336227308, "acc_stderr": 0.013373773411685644 } }, "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-6.7b,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": {} } }