lm_bff.json文件中相互关联的参数："inspired_templates", "replace_token_map_list"如何设置？

[pony-m]

[pony-m]

如下所示，是源代码中针对CoLA任务和数据集所设计的"inspired_templates", "replace_token_map_list"，我要进行MNLI任务，该如何设计对应的模板和参数？

{ "model_dir": "./models/t5-3b", "end_token": "", "beam": 100, "inspired_templates": ["*clssentu_0**<extra_id_0>label<extra_id_1>sep+", "cls.<extra_id_0>label<extra_id_1>+sentu_0sep+"], "target_number": 2, "batch_size": 32, "gen_max_len": 20, "truncates": ["head", "tail"], "first_mask_token": "<extra_id_0>", "forbid_tokens": [3, 19794, 22354], "forbid_continuous_token": [5], "replace_token_map_list": [{ "<extra_id_0>": "cls**sent_0", "<extra_id_1>": "mask", "<extra_id_2>": "sep+", "": "sep+", "▁":"_" }, { "<extra_id_0>": "cls", "<extra_id_1>": "mask", "<extra_id_2>": "+sent_0sep+", "": "+sent_0sep+*", "▁":"_" }] } 如果作者能整理出GLUE所有9项任务的参数设置，读者能更好地理解该方法。感谢作者~