修复ppo训练报错

backend/app/engines/text_engine.py

@@ -333,7 +333,7 @@ class TextEngine(BaseEngine):
                 gradient_accumulation_steps=gradient_accumulation,
                 ppo_epochs=ppo_epochs,
                 vf_coef=vf_coef,
-                kl_ctl=kl_coef,
+                init_kl_coef=kl_coef,
                 response_length=response_length,
                 output_dir=output_dir,
                 logging_steps=10,