{ "results": { "arc_challenge": { "acc": 0.302901023890785, "acc_stderr": 0.013428241573185349, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785564 }, "arc_easy": { "acc": 0.6494107744107744, "acc_stderr": 0.009791003829831557, "acc_norm": 0.5736531986531986, "acc_norm_stderr": 0.010147858603835144 }, "boolq": { "acc": 0.6284403669724771, "acc_stderr": 0.008451598145076589 }, "hellaswag": { "acc": 0.4649472216689902, "acc_stderr": 0.0049775044466089996, "acc_norm": 0.6228838876717785, "acc_norm_stderr": 0.004836738514051334 }, "lambada_openai": { "ppl": 6.619927277080142, "ppl_stderr": 0.1762520708430581, "acc": 0.5755870366776635, "acc_stderr": 0.006885918770006387 }, "openbookqa": { "acc": 0.252, "acc_stderr": 0.019435727282249536, "acc_norm": 0.358, "acc_norm_stderr": 0.021461434862859122 }, "piqa": { "acc": 0.7274211099020674, "acc_stderr": 0.010389256803296021, "acc_norm": 0.7366702937976061, "acc_norm_stderr": 0.010276185322196764 }, "sciq": { "acc": 0.901, "acc_stderr": 0.009449248027662765, "acc_norm": 0.845, "acc_norm_stderr": 0.011450157470799475 }, "siqa": { "acc": 0.4211873080859775, "acc_stderr": 0.011172633149198374, "acc_norm": 0.4498464687819857, "acc_norm_stderr": 0.011257008360485692 }, "winogrande": { "acc": 0.6464088397790055, "acc_stderr": 0.013436541262599948 } }, "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=bigscience/bloom-7b1,trust_remote_code=True,low_cpu_mem_usage=True,dtype=auto", "num_fewshot": 0, "batch_size": "8", "batch_sizes": [], "device": "cuda:5", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }