[mixed_batch=True]: Replace SameNlocBatchSampler with

[github-actions]

RandomSampler(replacement=False) + padding collate_fn.
Changes needed:

1. _collate_lmdb_batch: pad coord/force/atype to max_nloc,
   add "atom_mask" bool tensor (nframes, max_nloc)
2. Use RandomSampler(_data, replacement=False) as sampler
3. Use fixed batch_size in DataLoader (not batch_sampler)
4. Model forward: apply atom_mask to descriptor/fitting
5. Loss: mask out padded atoms in force loss

Line: 240

deepmd-kit/deepmd/pt/train/training.py

Lines 237 to 247 in 565f4be

	_data: LmdbDataset,
	) -> tuple[DataLoader, Generator[Any, None, None]]:
	if _data.mixed_batch:
	# TODO [mixed_batch=True]: Replace SameNlocBatchSampler with
	# RandomSampler(replacement=False) + padding collate_fn.
	# Changes needed:
	# 1. _collate_lmdb_batch: pad coord/force/atype to max_nloc,
	# add "atom_mask" bool tensor (nframes, max_nloc)
	# 2. Use RandomSampler(_data, replacement=False) as sampler
	# 3. Use fixed batch_size in DataLoader (not batch_sampler)
	# 4. Model forward: apply atom_mask to descriptor/fitting