diff --git a/src/llamafactory/data/loader.py b/src/llamafactory/data/loader.py
index 7d013d27..859f9a93 100644
--- a/src/llamafactory/data/loader.py
+++ b/src/llamafactory/data/loader.py
@@ -130,7 +130,7 @@ def get_dataset(
     model_args: "ModelArguments",
     data_args: "DataArguments",
     training_args: "Seq2SeqTrainingArguments",
-    stage: Literal["pt", "sft", "rm", "kto"],
+    stage: Literal["pt", "sft", "rm", "ppo", "kto"],
     tokenizer: "PreTrainedTokenizer",
     processor: Optional["ProcessorMixin"] = None,
 ) -> Union["Dataset", "IterableDataset"]:
diff --git a/src/llamafactory/data/preprocess.py b/src/llamafactory/data/preprocess.py
index 336257ca..97789c39 100644
--- a/src/llamafactory/data/preprocess.py
+++ b/src/llamafactory/data/preprocess.py
@@ -23,7 +23,7 @@ if TYPE_CHECKING:
 def get_preprocess_and_print_func(
     data_args: "DataArguments",
     training_args: "Seq2SeqTrainingArguments",
-    stage: Literal["pt", "sft", "rm", "kto"],
+    stage: Literal["pt", "sft", "rm", "ppo", "kto"],
     template: "Template",
     tokenizer: "PreTrainedTokenizer",
     processor: Optional["ProcessorMixin"],
diff --git a/src/llamafactory/data/processors/pretrain.py b/src/llamafactory/data/processors/pretrain.py
index 3de0d1ac..87727b55 100644
--- a/src/llamafactory/data/processors/pretrain.py
+++ b/src/llamafactory/data/processors/pretrain.py
@@ -18,7 +18,7 @@ def preprocess_pretrain_dataset(
         if data_args.template == "gemma":
             text_examples = [tokenizer.bos_token + example for example in text_examples]
 
-        result = tokenizer(text_examples, add_special_tokens=False, max_length=data_args.cutoff_len)
+        result = tokenizer(text_examples, add_special_tokens=False, max_length=data_args.cutoff_len, truncation=True)
     else:
         tokenized_examples = tokenizer(text_examples, add_special_tokens=False)
         concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}
diff --git a/src/llamafactory/train/ppo/workflow.py b/src/llamafactory/train/ppo/workflow.py
index c4e05e57..4383bcdc 100644
--- a/src/llamafactory/train/ppo/workflow.py
+++ b/src/llamafactory/train/ppo/workflow.py
@@ -29,7 +29,7 @@ def run_ppo(
 ):
     tokenizer_module = load_tokenizer(model_args)
     tokenizer = tokenizer_module["tokenizer"]
-    dataset = get_dataset(model_args, data_args, training_args, stage="pt", **tokenizer_module)
+    dataset = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
     model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
 
     tokenizer.padding_side = "left"  # use left-padding in generation while using right-padding in training