{ "results": { "pawsx_zh": { "acc": 0.452, "acc_stderr": 0.011131484850525779 }, "pawsx_de": { "acc": 0.528, "acc_stderr": 0.01116558709462154 }, "pawsx_ja": { "acc": 0.449, "acc_stderr": 0.011124809242874427 }, "pawsx_en": { "acc": 0.52, "acc_stderr": 0.011174185930778313 }, "pawsx_fr": { "acc": 0.4795, "acc_stderr": 0.011173732641806813 }, "pawsx_es": { "acc": 0.5325, "acc_stderr": 0.011159486640120933 }, "pawsx_ko": { "acc": 0.519, "acc_stderr": 0.011175058879956058 } }, "versions": { "pawsx_zh": 0, "pawsx_de": 0, "pawsx_ja": 0, "pawsx_en": 0, "pawsx_fr": 0, "pawsx_es": 0, "pawsx_ko": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-560m", "num_fewshot": 0, "batch_size": "auto", "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }