{ "results": { "piqa": { "acc": 0.7818280739934712, "acc_stderr": 0.009636081958374381, "acc_norm": 0.7742110990206746, "acc_norm_stderr": 0.00975498067091731 }, "wsc273": { "acc": 0.8095238095238095, "acc_stderr": 0.023809523809523777 }, "arc_easy": { "acc": 0.6738215488215489, "acc_stderr": 0.009619849417035172, "acc_norm": 0.5248316498316499, "acc_norm_stderr": 0.010247123122159281 }, "hellaswag": { "acc": 0.563931487751444, "acc_stderr": 0.004948824501355491, "acc_norm": 0.7298346942840072, "acc_norm_stderr": 0.004431375549911366 }, "winogrande": { "acc": 0.6692975532754538, "acc_stderr": 0.013222435887002705 }, "prost": { "acc": 0.2568851409052092, "acc_stderr": 0.003192056839011391, "acc_norm": 0.28031596925704527, "acc_norm_stderr": 0.0032814667207950675 }, "swag": { "acc": 0.5546835949215235, "acc_stderr": 0.0035138865053857436, "acc_norm": 0.6687493751874438, "acc_norm_stderr": 0.003327673972187388 }, "boolq": { "acc": 0.7305810397553517, "acc_stderr": 0.007759626474907443 }, "arc_challenge": { "acc": 0.3822525597269625, "acc_stderr": 0.014200454049979293, "acc_norm": 0.4138225255972696, "acc_norm_stderr": 0.014392730009221009 }, "mc_taco": { "em": 0.11261261261261261, "f1": 0.4827075067316446 }, "copa": { "acc": 0.84, "acc_stderr": 0.036845294917747094 }, "openbookqa": { "acc": 0.282, "acc_stderr": 0.020143572847290774, "acc_norm": 0.424, "acc_norm_stderr": 0.022122993778135404 } }, "versions": { "piqa": 0, "wsc273": 0, "arc_easy": 0, "hellaswag": 0, "winogrande": 0, "prost": 0, "swag": 0, "boolq": 1, "arc_challenge": 0, "mc_taco": 0, "copa": 0, "openbookqa": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/7B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }