{ "results": { "arc_challenge": { "acc": 0.3779863481228669, "acc_stderr": 0.014169664520303103, "acc_norm": 0.40017064846416384, "acc_norm_stderr": 0.014317197787809169 }, "arc_easy": { "acc": 0.7247474747474747, "acc_stderr": 0.009164888895174743, "acc_norm": 0.6771885521885522, "acc_norm_stderr": 0.009593950220366743 }, "boolq": { "acc": 0.7562691131498471, "acc_stderr": 0.007509067459407977 }, "hellaswag": { "acc": 0.5482971519617607, "acc_stderr": 0.004966448380104203, "acc_norm": 0.7389962158932484, "acc_norm_stderr": 0.004382844128643414 }, "lambada_openai": { "ppl": 3.827229437157901, "ppl_stderr": 0.07919367133146168, "acc": 0.7063846303124394, "acc_stderr": 0.006344860619678723 }, "openbookqa": { "acc": 0.314, "acc_stderr": 0.020776701920308997, "acc_norm": 0.398, "acc_norm_stderr": 0.02191237788577997 }, "piqa": { "acc": 0.7921653971708379, "acc_stderr": 0.009466997964536423, "acc_norm": 0.7976060935799782, "acc_norm_stderr": 0.00937428968280767 }, "sciq": { "acc": 0.948, "acc_stderr": 0.007024624213817142, "acc_norm": 0.919, "acc_norm_stderr": 0.00863212103213998 }, "siqa": { "acc": 0.41914022517911975, "acc_stderr": 0.011165140708170328, "acc_norm": 0.44319344933469806, "acc_norm_stderr": 0.011240812731564952 }, "winogrande": { "acc": 0.665351223362273, "acc_stderr": 0.013261823629558375 } }, "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=stablelm-3b-4e1t,dtype=bfloat16,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": {} } }