{ "results": { "arc_challenge": { "acc": 0.439419795221843, "acc_stderr": 0.014503747823580122, "acc_norm": 0.4462457337883959, "acc_norm_stderr": 0.014526705548539982 }, "prost": { "acc": 0.2688941076003416, "acc_stderr": 0.0032393206239968247, "acc_norm": 0.3052412467976089, "acc_norm_stderr": 0.003364432149066356 }, "swag": { "acc": 0.5673298010596821, "acc_stderr": 0.003502894135944166, "acc_norm": 0.6934919524142757, "acc_norm_stderr": 0.0032596605453371346 }, "arc_easy": { "acc": 0.7457912457912458, "acc_stderr": 0.008934537681141528, "acc_norm": 0.5989057239057239, "acc_norm_stderr": 0.010057051106534378 }, "boolq": { "acc": 0.6850152905198776, "acc_stderr": 0.00812432724981665 }, "wsc273": { "acc": 0.8608058608058609, "acc_stderr": 0.020988366070851 }, "mc_taco": { "em": 0.10960960960960961, "f1": 0.4753174430074593 }, "piqa": { "acc": 0.7883569096844396, "acc_stderr": 0.009530351270479397, "acc_norm": 0.7910772578890098, "acc_norm_stderr": 0.009485227030105093 }, "hellaswag": { "acc": 0.5910177255526787, "acc_stderr": 0.004906411984476791, "acc_norm": 0.7623979286994622, "acc_norm_stderr": 0.004247442237702478 }, "winogrande": { "acc": 0.7016574585635359, "acc_stderr": 0.012858885010030434 }, "copa": { "acc": 0.9, "acc_stderr": 0.030151134457776348 }, "openbookqa": { "acc": 0.306, "acc_stderr": 0.020629569998345403, "acc_norm": 0.422, "acc_norm_stderr": 0.022109039310618552 } }, "versions": { "arc_challenge": 0, "prost": 0, "swag": 0, "arc_easy": 0, "boolq": 1, "wsc273": 0, "mc_taco": 0, "piqa": 0, "hellaswag": 0, "winogrande": 0, "copa": 0, "openbookqa": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/13B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }