{ "results": { "copa": { "acc": 0.69, "acc_stderr": 0.04648231987117316 }, "mc_taco": { "em": 0.1403903903903904, "f1": 0.40416372323956457 }, "prost": { "acc": 0.24044619982920581, "acc_stderr": 0.003122204753095043, "acc_norm": 0.3104718189581554, "acc_norm_stderr": 0.0033803389886508614 }, "piqa": { "acc": 0.6512513601741022, "acc_stderr": 0.011119263056159583, "acc_norm": 0.6485310119695321, "acc_norm_stderr": 0.011139207691931193 }, "wsc273": { "acc": 0.5860805860805861, "acc_stderr": 0.029864284486117058 }, "winogrande": { "acc": 0.5248618784530387, "acc_stderr": 0.01403510288362775 }, "swag": { "acc": 0.4111266620013996, "acc_stderr": 0.0034788002208961154, "acc_norm": 0.5425872238328502, "acc_norm_stderr": 0.003522245713261821 }, "boolq": { "acc": 0.5333333333333333, "acc_stderr": 0.008725599880049204 }, "hellaswag": { "acc": 0.30780720971917946, "acc_stderr": 0.004606429684604547, "acc_norm": 0.3520215096594304, "acc_norm_stderr": 0.004766245539606642 }, "arc_challenge": { "acc": 0.19965870307167236, "acc_stderr": 0.011681625756888688, "acc_norm": 0.24232081911262798, "acc_norm_stderr": 0.012521593295800113 }, "arc_easy": { "acc": 0.45707070707070707, "acc_stderr": 0.010221897564256037, "acc_norm": 0.41203703703703703, "acc_norm_stderr": 0.010099765857562767 }, "openbookqa": { "acc": 0.15, "acc_stderr": 0.015984712135164926, "acc_norm": 0.288, "acc_norm_stderr": 0.020271503835075214 } }, "versions": { "copa": 0, "mc_taco": 0, "prost": 0, "piqa": 0, "wsc273": 0, "winogrande": 0, "swag": 0, "boolq": 1, "hellaswag": 0, "arc_challenge": 0, "arc_easy": 0, "openbookqa": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=facebook/xglm-564M,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }