From cc1a595c630d0c4409e9ad1db0c9d0cb70c1043a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E4=BD=95=E6=B2=BB=E9=9D=99?= Date: Mon, 21 Mar 2022 12:56:48 +0000 Subject: [PATCH] update PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md. --- PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md b/PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md index 0c4b6f6384..312e570726 100644 --- a/PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md +++ b/PyTorch/built-in/nlp/mBART_ID2372_for_PyTorch/README.md @@ -111,8 +111,8 @@ fairseq-preprocess \ # 在数据集上进行fine-tune ```bash -1. 修改run_8p.sh中PRETRAIN为模型的路径，DATA_PATH为数据集的路径 - [若需要训练en_de数据集，则需要将run_8p.sh中dropout的参数设置为0.1,total-num-update与max-update设置为300000] +1. 修改run_8p.sh中PRETRAIN为模型的路径，DATA_PATH为数据集的路径（train_data/en_ro 或train_data/en_de） + [若需要训练en_de数据集，则需要将run_8p.sh中dropout的参数设置为0.1,total-num-update与max-update设置为300000，target-lang设置为de_DE] 2. 执行 bash run_8p.sh ``` # 在数据集上进行评估 -- Gitee