@@ -11,8 +11,6 @@ class Dataset(BaseUI):
1111
1212 group = 'llm_train'
1313
14- is_studio = os .environ .get ('MODELSCOPE_ENVIRONMENT' ) == 'studio'
15-
1614 locale_dict = {
1715 'dataset' : {
1816 'label' : {
@@ -70,11 +68,8 @@ class Dataset(BaseUI):
7068 'en' : 'The sample size from the train dataset'
7169 },
7270 'info' : {
73- 'zh' :
74- '从训练集中采样一定行数进行训练' if not is_studio else '为减少训练时间, 采样数量在space/studio条件下不可选' ,
75- 'en' :
76- 'Train with the sample size from the dataset'
77- if not is_studio else 'Not interactive in space/studio to reduce train time' ,
71+ 'zh' : '从训练集中采样一定行数进行训练' ,
72+ 'en' : 'Train with the sample size from the dataset' ,
7873 }
7974 },
8075 'val_dataset_sample' : {
@@ -83,11 +78,8 @@ class Dataset(BaseUI):
8378 'en' : 'The sample size from the val dataset'
8479 },
8580 'info' : {
86- 'zh' :
87- '从验证集中采样一定行数进行训练' if not is_studio else '为减少训练时间, 采样数量在space/studio条件下不可选' ,
88- 'en' :
89- 'Validate with the sample size from the dataset'
90- if not is_studio else 'Not interactive in space/studio to reduce train time' ,
81+ 'zh' : '从验证集中采样一定行数进行训练' ,
82+ 'en' : 'Validate with the sample size from the dataset' ,
9183 }
9284 },
9385 'truncation_strategy' : {
@@ -103,11 +95,11 @@ class Dataset(BaseUI):
10395 'custom_dataset_info' : {
10496 'label' : {
10597 'zh' : '外部数据集配置' ,
106- 'en' : 'An outer dataset config'
98+ 'en' : 'Custom dataset config'
10799 },
108100 'info' : {
109101 'zh' : '注册外部数据集的配置文件' ,
110- 'en' : 'How to deal with the rows exceed the max length '
102+ 'en' : 'An extra dataset config to register your own datasets '
111103 }
112104 },
113105 }
0 commit comments