{ "results": { "arc_challenge": { "acc": 0.318259385665529, "acc_stderr": 0.013611993916971451, "acc_norm": 0.3532423208191126, "acc_norm_stderr": 0.013967822714840055 }, "arc_easy": { "acc": 0.6721380471380471, "acc_stderr": 0.009632587076170013, "acc_norm": 0.6106902356902357, "acc_norm_stderr": 0.010005212782878145 }, "boolq": { "acc": 0.6400611620795107, "acc_stderr": 0.008394940698368873 }, "hellaswag": { "acc": 0.48048197570205137, "acc_stderr": 0.0049859782149379184, "acc_norm": 0.6388169687313284, "acc_norm_stderr": 0.004793617835645056 }, "lambada_openai": { "ppl": 4.457423605452202, "ppl_stderr": 0.10007464956313723, "acc": 0.670095090238696, "acc_stderr": 0.00655050345779628 }, "openbookqa": { "acc": 0.258, "acc_stderr": 0.019586711785215837, "acc_norm": 0.372, "acc_norm_stderr": 0.0216371979857224 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.01009188277012022, "acc_norm": 0.76550598476605, "acc_norm_stderr": 0.009885203143240538 }, "sciq": { "acc": 0.898, "acc_stderr": 0.00957536880165389, "acc_norm": 0.84, "acc_norm_stderr": 0.011598902298689004 }, "siqa": { "acc": 0.40736949846468784, "acc_stderr": 0.011118216651888717, "acc_norm": 0.42988741044012285, "acc_norm_stderr": 0.011202283451328794 }, "winogrande": { "acc": 0.606156274664562, "acc_stderr": 0.013732114472668745 } }, "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": "pretrained=EleutherAI/pythia-6.9b,dtype=float16,trust_remote_code=True,low_cpu_mem_usage=True,use_fast=True", "num_fewshot": 0, "batch_size": "8", "batch_sizes": [], "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }