1. add custom eval dataset support

2. merge load dataset and split dataset function


Former-commit-id: 963d97ba07e7efa3a4544c4d077283d9e112b3ad

src/llamafactory/hparams/data_args.py

@@ -33,6 +33,11 @@ class DataArguments:
         default=None,
         metadata={"help": "The name of provided dataset(s) to use. Use commas to separate multiple datasets."},
     )
+    eval_dataset: Optional[str] = field(
+        default=None,
+        metadata={"help": "The name of provided dataset(s) to use for eval during training. "
+                          "Use commas to separate multiple datasets."},
+    )
     dataset_dir: str = field(
         default="data",
         metadata={"help": "Path to the folder containing the datasets."},
@@ -105,6 +110,10 @@ class DataArguments:
         default=None,
         metadata={"help": "Path to save or load the tokenized datasets."},
     )
+    eval_tokenized_path: Optional[str] = field(
+        default=None,
+        metadata={"help": "Path to save or load the tokenized eval datasets."},
+    )
 
     def __post_init__(self):
         if self.streaming and self.val_size > 1e-6 and self.val_size < 1: