{ "results": { "mc_taco": { "em": 0.12537537537537538, "f1": 0.47458014393437276 }, "arc_easy": { "acc": 0.5631313131313131, "acc_stderr": 0.010177672928157678, "acc_norm": 0.4810606060606061, "acc_norm_stderr": 0.010252420496894487 }, "boolq": { "acc": 0.617737003058104, "acc_stderr": 0.008499149690449272 }, "piqa": { "acc": 0.6877040261153428, "acc_stderr": 0.010812581599154424, "acc_norm": 0.7007616974972797, "acc_norm_stderr": 0.010684130673134581 }, "copa": { "acc": 0.7, "acc_stderr": 0.046056618647183814 }, "prost": { "acc": 0.23521562766865928, "acc_stderr": 0.003098672944164254, "acc_norm": 0.2669726729291204, "acc_norm_stderr": 0.00323196492387981 }, "hellaswag": { "acc": 0.37621987651862177, "acc_stderr": 0.004834461997944872, "acc_norm": 0.46564429396534557, "acc_norm_stderr": 0.004977988452502641 }, "swag": { "acc": 0.4532140357892632, "acc_stderr": 0.0035195819088979174, "acc_norm": 0.6114665600319904, "acc_norm_stderr": 0.003446127007510879 }, "openbookqa": { "acc": 0.214, "acc_stderr": 0.01835979750238702, "acc_norm": 0.3, "acc_norm_stderr": 0.020514426225628046 }, "wsc273": { "acc": 0.7289377289377289, "acc_stderr": 0.02695226692070332 }, "arc_challenge": { "acc": 0.2354948805460751, "acc_stderr": 0.012399451855004752, "acc_norm": 0.26791808873720135, "acc_norm_stderr": 0.012942030195136423 }, "winogrande": { "acc": 0.5714285714285714, "acc_stderr": 0.013908353814606709 } }, "versions": { "mc_taco": 0, "arc_easy": 0, "boolq": 1, "piqa": 0, "copa": 0, "prost": 0, "hellaswag": 0, "swag": 0, "openbookqa": 0, "wsc273": 0, "arc_challenge": 0, "winogrande": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-1b7,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }