{ "results": { "pawsx_zh": { "acc": 0.4735, "acc_stderr": 0.011167418260963935 }, "pawsx_de": { "acc": 0.5285, "acc_stderr": 0.011164954236428803 }, "pawsx_en": { "acc": 0.613, "acc_stderr": 0.010893798117218195 }, "pawsx_ko": { "acc": 0.451, "acc_stderr": 0.01112930504188632 }, "pawsx_fr": { "acc": 0.509, "acc_stderr": 0.011181324206260283 }, "pawsx_es": { "acc": 0.5935, "acc_stderr": 0.010985864536294245 }, "pawsx_ja": { "acc": 0.4545, "acc_stderr": 0.01113673598700373 } }, "versions": { "pawsx_zh": 0, "pawsx_de": 0, "pawsx_en": 0, "pawsx_ko": 0, "pawsx_fr": 0, "pawsx_es": 0, "pawsx_ja": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-7b1", "num_fewshot": 0, "batch_size": "auto", "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }