diff --git a/wall_x/trainer/qwen_vl_act_trainer.py b/wall_x/trainer/qwen_vl_act_trainer.py
index 05dc648..4a04cd7 100644
--- a/wall_x/trainer/qwen_vl_act_trainer.py
+++ b/wall_x/trainer/qwen_vl_act_trainer.py
@@ -197,6 +197,9 @@ class QwenVlAct_Trainer:
             self.train_loop(epoch)
             self.accelerator.wait_for_everyone()
             
+            if (epoch + 1) % self.config.get("epoch_save_interval", 10) == 0:
+                self.save_checkpoint(epoch)
+            
             # Validation after each epoch
             self.val_loop()
             self.accelerator.wait_for_everyone()
diff --git a/workspace/lerobot_example/config_qact.yml b/workspace/lerobot_example/config_qact.yml
index b4d2fea..83e8d50 100644
--- a/workspace/lerobot_example/config_qact.yml
+++ b/workspace/lerobot_example/config_qact.yml
@@ -5,9 +5,8 @@
 log_name: "robotic_training"
 log_project: "vla_training"
 model_type: qwen2_5
-pretrained_qwen_vl_path: "/path/to/qwen_vl_model/"
-# whether to enable fast tokenizer
-use_fast_tokenizer: false
+pretrained_qwen_vl_path: "/path/to/wallx_model/"
+use_fast_tokenizer: false # True: train FAST, False: train Flow
 action_tokenizer_path: "/path/to/fast/"
 save_path: "/path/to/workspace/"
 
@@ -27,6 +26,7 @@ num_epoch: 100
 gradient_accumulation_steps: 32
 batch_size_per_gpu: 8
 padding_side: left
+epoch_save_interval: 10
 
 # Robot configuration - Define degrees of freedom for each component
 dof_config: