{ "results": { "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "arc_challenge": { "acc": 0.2713310580204778, "acc_stderr": 0.012993807727545796, "acc_norm": 0.2815699658703072, "acc_norm_stderr": 0.01314337673500902 }, "mc_taco": { "em": 0.1539039039039039, "f1": 0.435083658174568 }, "prost": { "acc": 0.26430401366353545, "acc_stderr": 0.003221619340165698, "acc_norm": 0.2627561912894962, "acc_norm_stderr": 0.003215549484247182 }, "piqa": { "acc": 0.7274211099020674, "acc_stderr": 0.01038925680329602, "acc_norm": 0.7295973884657236, "acc_norm_stderr": 0.010363167031620785 }, "wsc273": { "acc": 0.717948717948718, "acc_stderr": 0.027285147081637318 }, "winogrande": { "acc": 0.5611681136543015, "acc_stderr": 0.013946933444507032 }, "boolq": { "acc": 0.6119266055045871, "acc_stderr": 0.008523130584760844 }, "openbookqa": { "acc": 0.232, "acc_stderr": 0.018896193591952045, "acc_norm": 0.344, "acc_norm_stderr": 0.02126575803797874 }, "arc_easy": { "acc": 0.6031144781144782, "acc_stderr": 0.010039236800583206, "acc_norm": 0.5723905723905723, "acc_norm_stderr": 0.010151683397430673 }, "hellaswag": { "acc": 0.43766182035451107, "acc_stderr": 0.004950848456984543, "acc_norm": 0.5823541127265485, "acc_norm_stderr": 0.004921632645102376 }, "swag": { "acc": 0.49650104968509445, "acc_stderr": 0.0035350054881690377, "acc_norm": 0.6786963910826752, "acc_norm_stderr": 0.0033016139730438565 } }, "versions": { "copa": 0, "arc_challenge": 0, "mc_taco": 0, "prost": 0, "piqa": 0, "wsc273": 0, "winogrande": 0, "boolq": 1, "openbookqa": 0, "arc_easy": 0, "hellaswag": 0, "swag": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=facebook/xglm-4.5B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }