fix : FSDP 优化器顺序、温度除零、调度器静默死亡、ref模型设备

- executor: use_orig_params 硬编码 True，FSDP 不替换 Parameter 对象
- strategy: DPO/GRPO ref 模型创建后移到 device
- sample: TemperatureStrategy clamp 1e-8，engine 验证改为 >0
- scheduler: 异常不 re-raise 避免 daemon 静默死亡，stop() 发回调给 waiting 任务

astrai/trainer/strategy.py

@@ -219,7 +219,7 @@ class DPOStrategy(BaseStrategy):
         super().__init__(model, device, **kwargs)
         self.ref_model = create_ref_model(
             self.model_fn, self.executor.unwrap_model(model)
-        )
+        ).to(device=self.device)
         self.beta = beta
         self.reduction = reduction
 
@@ -275,7 +275,7 @@ class GRPOStrategy(BaseStrategy):
         super().__init__(model, device, **kwargs)
         self.ref_model = create_ref_model(
             self.model_fn, self.executor.unwrap_model(model)
-        )
+        ).to(device=self.device)
         self.clip_eps = clip_eps
         self.kl_coef = kl_coef
         self.group_size = group_size