feat: Checkpoint 支持 extra 通用扩展数据，用户通过函数自定义保存/恢复优化器等状态

- serialization.py: Checkpoint 新增 extra: dict 字段，
  save() 写入 extra.pt，load() 自动恢复
- train_callback.py: CheckpointCallback 新增 save_extra_fn
  参数，用户传入 (context) -> dict 决定保存哪些额外状态
- train_context.py: TrainContextBuilder 新增 load_extra_fn
  参数，用户传入 (extra, context) 从 checkpoint 恢复状态

astrai/trainer/train_context.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass, field
-from typing import Optional, Self
+from typing import Callable, Optional, Self
 
 import torch.nn as nn
 from torch.optim import Optimizer
@@ -32,9 +32,14 @@ class TrainContext:
 
 
 class TrainContextBuilder:
-    def __init__(self, config: TrainConfig):
+    def __init__(
+        self,
+        config: TrainConfig,
+        load_extra_fn: Optional[Callable[[dict, "TrainContext"], None]] = None,
+    ):
         self.config = config
         self._checkpoint: Optional[Checkpoint] = None
+        self._load_extra_fn = load_extra_fn
 
     def with_checkpoint(self, checkpoint: Optional[Checkpoint]) -> Self:
         self._checkpoint = checkpoint
@@ -66,6 +71,9 @@ class TrainContextBuilder:
         context.optimizer = self.config.optimizer_fn(context.model)
         context.scheduler = self.config.scheduler_fn(context.optimizer)
 
+        if self._checkpoint and self._checkpoint.extra and self._load_extra_fn:
+            self._load_extra_fn(self._checkpoint.extra, context)
+
         cfg = self.config
         sampler_offset = context.iteration * cfg.batch_size
         sampler = ResumableDistributedSampler(