seqio.get_mixture_or_task('ag_news_subset_template_0_five_shot') failed

python script:
selected_mixture = seqio.get_mixture_or_task('ag_news_subset_template_0_five_shot')
INPUT_SEQ_LEN = 2056
TARGET_SEQ_LEN = 512

dataset = selected_mixture.get_dataset(
sequence_length={"inputs": INPUT_SEQ_LEN, "targets": TARGET_SEQ_LEN},
# split="train",
shuffle=True,
num_epochs=1,
# shard_info=seqio.ShardInfo(index=0, num_shards=10),
use_cached=False,
seed=42
)
for i, ex in enumerate(dataset.take(10)):
print(ex)

this script will report errors：

but when i replace
selected_mixture = seqio.get_mixture_or_task('ag_news_subset_template_0_five_shot')
with
selected_mixture = seqio.get_mixture_or_task('ag_news_subset_template_mix_five_shot')
the result is success, why?

Start by reproducing the provided Python script with ag_news_subset_template_0_five_shot, then compare its behavior with ag_news_subset_template_mix_five_shot. Inspect the mixture and task definitions referenced by these names and identify why one fails during get_dataset; done means the failing lookup or dataset construction is explained and the reported case works or is documented as unsupported.

Written by the indexing model from the issue text.