1. add custom eval dataset support

2. merge load dataset and split dataset function


Former-commit-id: 76f3bbcfc0

data/README.md

@@ -12,7 +12,8 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
   "ranking": "whether the dataset is a preference dataset or not. (default: False)",
   "subset": "the name of the subset. (optional, default: None)",
   "folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
-  "num_samples": "the number of samples in the dataset used for training. (optional, default: None)",
+  "num_samples": "the number of samples in the dataset used for training. (optional, default: None)", 
+  "split": "which dataset split to use for training and evaluation (optional, default: train)",
   "columns (optional)": {
     "prompt": "the column name in the dataset containing the prompts. (default: instruction)",
     "query": "the column name in the dataset containing the queries. (default: input)",

data/README_zh.md

@@ -13,6 +13,7 @@
   "subset": "数据集子集的名称（可选，默认：None）",
   "folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
   "num_samples": "该数据集中用于训练的样本数量。（可选，默认：None）",
+  "split": "数据集中的要使用的训练测试集切分（可选，默认：train）",
   "columns（可选）": {
     "prompt": "数据集代表提示词的表头名称（默认：instruction）",
     "query": "数据集代表请求的表头名称（默认：input）",

data/dataset_info.json

@@ -172,9 +172,19 @@
   "deepctrl": {
     "ms_hub_url": "deepctrl/deepctrl-sft-data"
   },
-  "adgen": {
+  "adgen_train": {
     "hf_hub_url": "HasturOfficial/adgen",
     "ms_hub_url": "AI-ModelScope/adgen",
+    "split": "train",
+    "columns": {
+      "prompt": "content",
+      "response": "summary"
+    }
+  },
+  "adgen_val": {
+    "hf_hub_url": "HasturOfficial/adgen",
+    "ms_hub_url": "AI-ModelScope/adgen",
+    "split": "validation",
     "columns": {
       "prompt": "content",
       "response": "summary"