{ "results": { "arc_challenge": { "acc": 0.318259385665529, "acc_stderr": 0.013611993916971451, "acc_norm": 0.3506825938566553, "acc_norm_stderr": 0.013944635930726083 }, "arc_easy": { "acc": 0.702020202020202, "acc_stderr": 0.009385046066694871, "acc_norm": 0.6372053872053872, "acc_norm_stderr": 0.00986593675701393 }, "boolq": { "acc": 0.6730886850152905, "acc_stderr": 0.008204340208838751 }, "hellaswag": { "acc": 0.5046803425612428, "acc_stderr": 0.004989562798280524, "acc_norm": 0.673770165305716, "acc_norm_stderr": 0.004678743563766643 }, "lambada_openai": { "ppl": 3.9264187287921497, "ppl_stderr": 0.08375179732007268, "acc": 0.7063846303124394, "acc_stderr": 0.006344860619678724 }, "openbookqa": { "acc": 0.264, "acc_stderr": 0.019732885585922108, "acc_norm": 0.372, "acc_norm_stderr": 0.0216371979857224 }, "piqa": { "acc": 0.7627856365614799, "acc_stderr": 0.009924694933586366, "acc_norm": 0.7698585418933623, "acc_norm_stderr": 0.009820832826839798 }, "sciq": { "acc": 0.902, "acc_stderr": 0.009406619184621235, "acc_norm": 0.851, "acc_norm_stderr": 0.011266140684632175 }, "siqa": { "acc": 0.4201637666325486, "acc_stderr": 0.011168911571162012, "acc_norm": 0.44268167860798363, "acc_norm_stderr": 0.011239482425741961 }, "winogrande": { "acc": 0.6400947119179163, "acc_stderr": 0.013489609590266804 } }, "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-12b,dtype=float16,trust_remote_code=True,low_cpu_mem_usage=True,use_fast=True", "num_fewshot": 0, "batch_size": "1", "batch_sizes": [], "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }