{ "results": { "arc_challenge": { "acc": 0.2363481228668942, "acc_stderr": 0.012414960524301829, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768407 }, "arc_easy": { "acc": 0.4473905723905724, "acc_stderr": 0.010202832385415646, "acc_norm": 0.42045454545454547, "acc_norm_stderr": 0.010129114278546535 }, "boolq": { "acc": 0.5764525993883792, "acc_stderr": 0.008642220663071512 }, "hellaswag": { "acc": 0.329416450906194, "acc_stderr": 0.004690407826933909, "acc_norm": 0.38309101772555265, "acc_norm_stderr": 0.004851466623601455 }, "lambada_openai": { "ppl": 20.187359473367042, "ppl_stderr": 0.7391414436494796, "acc": 0.4172326799922375, "acc_stderr": 0.006869874864639983 }, "openbookqa": { "acc": 0.17, "acc_stderr": 0.016815633531393422, "acc_norm": 0.294, "acc_norm_stderr": 0.020395095484936614 }, "sciq": { "acc": 0.717, "acc_stderr": 0.01425181090648174, "acc_norm": 0.649, "acc_norm_stderr": 0.015100563798316403 }, "siqa": { "acc": 0.3561924257932446, "acc_stderr": 0.010836006561369118, "acc_norm": 0.4094165813715456, "acc_norm_stderr": 0.01112684957658903 }, "piqa": { "acc": 0.6381936887921654, "acc_stderr": 0.011211397313020371, "acc_norm": 0.6273122959738846, "acc_norm_stderr": 0.01128131833289774 }, "truthfulqa_mc": { "mc1": 0.22399020807833536, "mc1_stderr": 0.014594964329474205, "mc2": 0.4052844601694033, "mc2_stderr": 0.014547007787950397 }, "winogrande": { "acc": 0.526440410418311, "acc_stderr": 0.014032823874407229 } }, "versions": { "arc_challenge": 0, "arc_easy": 0, "boolq": 1, "hellaswag": 0, "lambada_openai": 0, "openbookqa": 0, "piqa": 0, "sciq": 0, "siqa": 0, "truthfulqa_mc": 1, "winogrande": 0 }, "config": { "model": "gpt2", "model_args": "use_fast=True,pretrained=stabilityai/stablelm-base-alpha-3b,trust_remote_code=True,low_cpu_mem_usage=True,dtype=auto", "num_fewshot": 0, "batch_size": "8", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }