refactor: checkpoint 按 HF 方式存独立 .pt 文件，callback 接管恢复

- Checkpoint.save/load: extra 逐 key 写为 {key}.pt 而非单个 extra.pt
- meta.json 新增 timestamp
- CheckpointCallback: save_extra/load_extra 静态方法 + extra_keys 类属性
- on_train_begin 接管 optimizer/scheduler 恢复，TrainContextBuilder 不再传 load_extra_fn

astrai/trainer/train_callback.py

@@ -90,6 +90,8 @@ class CheckpointCallback(TrainCallback):
     Checkpoint callback for trainer.
     """
 
+    extra_keys = ("optimizer", "scheduler")
+
     def __init__(
         self,
         save_dir: str,
@@ -97,12 +99,14 @@ class CheckpointCallback(TrainCallback):
         weight_only: bool = False,
         state_dict_fn: Optional[Callable[[nn.Module], dict]] = None,
         save_extra_fn: Optional[Callable[["TrainContext"], dict]] = None,
+        load_extra_fn: Optional[Callable[[dict, "TrainContext"], None]] = None,
     ):
         self.save_dir = save_dir
         self.interval = interval
         self.weight_only = weight_only
         self.state_dict_fn = state_dict_fn
-        self.save_extra_fn = save_extra_fn
+        self.save_extra_fn = save_extra_fn or CheckpointCallback.save_extra
+        self.load_extra_fn = load_extra_fn or CheckpointCallback.load_extra
         self.last_ckpt_iter = 0
 
     @only_on_rank(0)
@@ -116,7 +120,7 @@ class CheckpointCallback(TrainCallback):
             else context.model.state_dict()
         )
 
-        extra = self.save_extra_fn(context) if self.save_extra_fn else None
+        extra = self.save_extra_fn(context)
         context.checkpoint = Checkpoint(
             state_dict=state_dict,
             epoch=context.epoch,
@@ -127,6 +131,10 @@ class CheckpointCallback(TrainCallback):
         context.checkpoint.save(save_path)
         self.last_ckpt_iter = context.iteration
 
+    def on_train_begin(self, context: TrainContext):
+        if context.checkpoint and context.checkpoint.extra:
+            self.load_extra_fn(context.checkpoint.extra, context)
+
     def on_batch_end(self, context: TrainContext):
         if context.iteration - self.last_ckpt_iter >= self.interval:
             self._save_checkpoint(context)
@@ -138,6 +146,21 @@ class CheckpointCallback(TrainCallback):
     def on_error(self, context: TrainContext):
         self._save_checkpoint(context)
 
+    @staticmethod
+    def save_extra(context: TrainContext) -> dict:
+        extra = {}
+        for name in CheckpointCallback.extra_keys:
+            obj = getattr(context, name, None)
+            if obj:
+                extra[name] = obj.state_dict()
+        return extra
+
+    @staticmethod
+    def load_extra(extra: dict, context: TrainContext):
+        for name in CheckpointCallback.extra_keys:
+            if name in extra:
+                getattr(context, name).load_state_dict(extra[name])
+
 
 @CallbackFactory.register("progress_bar")
 class ProgressBarCallback(TrainCallback):

astrai/trainer/train_context.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass, field
-from typing import Callable, Optional, Self
+from typing import Optional, Self
 
 import torch.nn as nn
 from torch.optim import Optimizer
@@ -35,11 +35,9 @@ class TrainContextBuilder:
     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
@@ -71,9 +69,6 @@ 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(