{ "results": { "piqa": { "acc": 0.7127312295973884, "acc_stderr": 0.010557291761528637, "acc_norm": 0.7301414581066377, "acc_norm_stderr": 0.010356595421852193 }, "openbookqa": { "acc": 0.216, "acc_stderr": 0.01842190906141194, "acc_norm": 0.332, "acc_norm_stderr": 0.021081766571222856 }, "arc_challenge": { "acc": 0.23464163822525597, "acc_stderr": 0.01238387356076868, "acc_norm": 0.2738907849829352, "acc_norm_stderr": 0.013032004972989505 }, "arc_easy": { "acc": 0.5664983164983165, "acc_stderr": 0.010168640625454107, "acc_norm": 0.5336700336700336, "acc_norm_stderr": 0.010236494647406476 }, "boolq": { "acc": 0.6143730886850153, "acc_stderr": 0.008513189460768057 }, "wsc273": { "acc": 0.7106227106227107, "acc_stderr": 0.027495860234525278 }, "copa": { "acc": 0.74, "acc_stderr": 0.04408440022768077 }, "hellaswag": { "acc": 0.4091814379605656, "acc_stderr": 0.004906779523192668, "acc_norm": 0.5370444134634534, "acc_norm_stderr": 0.004976067726432559 }, "prost": { "acc": 0.21920367207514946, "acc_stderr": 0.003022497462586152, "acc_norm": 0.2664389410760034, "acc_norm_stderr": 0.0032299078734217036 }, "swag": { "acc": 0.4849045286414076, "acc_stderr": 0.0035334805738792946, "acc_norm": 0.6578026592022393, "acc_norm_stderr": 0.0033544154500719224 }, "mc_taco": { "em": 0.11936936936936937, "f1": 0.4779548809969738 }, "winogrande": { "acc": 0.5461720599842147, "acc_stderr": 0.013992441563707058 } }, "versions": { "piqa": 0, "openbookqa": 0, "arc_challenge": 0, "arc_easy": 0, "boolq": 1, "wsc273": 0, "copa": 0, "hellaswag": 0, "prost": 0, "swag": 0, "mc_taco": 0, "winogrande": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=facebook/xglm-2.9B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }