-
Notifications
You must be signed in to change notification settings - Fork 3k
Description
Describe the bug
Traceback (most recent call last):
File "/workspace/ctn.py", line 8, in
ds = load_dataset(f"naver-clova-ix/synthdog-{lang}") # или "synthdog-zh" для китайского
File "/workspace/.venv/lib/python3.14/site-packages/datasets/load.py", line 1397, in load_dataset
builder_instance = load_dataset_builder(
path=path,
...<10 lines>...
**config_kwargs,
)
File "/workspace/.venv/lib/python3.14/site-packages/datasets/load.py", line 1185, in load_dataset_builder
builder_instance._use_legacy_cache_dir_if_possible(dataset_module)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/builder.py", line 612, in _use_legacy_cache_dir_if_possible
self._check_legacy_cache2(dataset_module) or self._check_legacy_cache() or None
~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/builder.py", line 485, in _check_legacy_cache2
config_id = self.config.name + "-" + Hasher.hash({"data_files": self.config.data_files})
~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/fingerprint.py", line 188, in hash
return cls.hash_bytes(dumps(value))
~~~~~^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/utils/_dill.py", line 120, in dumps
dump(obj, file)
~~~~^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/utils/_dill.py", line 114, in dump
Pickler(file, recurse=True).dump(obj)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/dill/_dill.py", line 428, in dump
StockPickler.dump(self, obj)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^
File "/usr/lib/python3.14/pickle.py", line 498, in dump
self.save(obj)
~~~~~~~~~^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/datasets/utils/_dill.py", line 70, in save
dill.Pickler.save(self, obj, save_persistent_id=save_persistent_id)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/dill/_dill.py", line 422, in save
StockPickler.save(self, obj, save_persistent_id)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.14/pickle.py", line 572, in save
f(self, obj) # Call unbound method with explicit self
~^^^^^^^^^^^
File "/workspace/.venv/lib/python3.14/site-packages/dill/_dill.py", line 1262, in save_module_dict
StockPickler.save_dict(pickler, obj)
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^
File "/usr/lib/python3.14/pickle.py", line 1064, in save_dict
self._batch_setitems(obj.items(), obj)
~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
TypeError: Pickler._batch_setitems() takes 2 positional arguments but 3 were given
Steps to reproduce the bug
ds_train = ds["train"].map(lambda x: {**x, "lang": lang})
Expected behavior
Fixed bugs
Environment info
datasets
version: 4.2.0- Platform: Linux-6.8.0-85-generic-x86_64-with-glibc2.39
- Python version: 3.14.0
huggingface_hub
version: 0.35.3- PyArrow version: 21.0.0
- Pandas version: 2.3.3
fsspec
version: 2025.9.0