change to right-padding, update reward score #803

Former-commit-id: baa90415bc8f5ebd423d001378b51c3a3a6c2ec7

src/llmtuner/hparams/data_args.py

@@ -26,7 +26,8 @@ class DataArguments:
     r"""
     Arguments pertaining to what data we are going to input our model for training and evaluation.
     """
-    template: str = field(
+    template: Optional[str] = field(
+        default=None,
         metadata={"help": "Which template to use for constructing prompts in training and inference."}
     )
     dataset: Optional[str] = field(
@@ -46,7 +47,7 @@ class DataArguments:
         metadata={"help": "Enable streaming mode."}
     )
     buffer_size: Optional[int] = field(
-        default=16384,
+        default=1024,
         metadata={"help": "Size of the buffer to randomly sample examples from in streaming mode."}
     )
     mix_strategy: Optional[Literal["concat", "interleave_under", "interleave_over"]] = field(

src/llmtuner/hparams/model_args.py

@@ -27,10 +27,6 @@ class ModelArguments:
         default="main",
         metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."}
     )
-    padding_side: Optional[Literal["left", "right"]] = field(
-        default="left",
-        metadata={"help": "The side on which the model should have padding applied."}
-    )
     quantization_bit: Optional[int] = field(
         default=None,
         metadata={"help": "The number of bits to quantize the model."}