{ "results": { "pawsx_ja": { "acc": 0.447, "acc_stderr": 0.011120131683767737 }, "pawsx_es": { "acc": 0.513, "acc_stderr": 0.011179355482070377 }, "pawsx_fr": { "acc": 0.462, "acc_stderr": 0.01115079235234166 }, "pawsx_de": { "acc": 0.4875, "acc_stderr": 0.011179640744835734 }, "pawsx_ko": { "acc": 0.458, "acc_stderr": 0.011143612073516636 }, "pawsx_zh": { "acc": 0.454, "acc_stderr": 0.0111357084193598 }, "pawsx_en": { "acc": 0.489, "acc_stderr": 0.011180429374603775 } }, "versions": { "pawsx_ja": 0, "pawsx_es": 0, "pawsx_fr": 0, "pawsx_de": 0, "pawsx_ko": 0, "pawsx_zh": 0, "pawsx_en": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-1b7", "num_fewshot": 0, "batch_size": "auto", "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }