"glue/qqp" DownloadError

[puleon]

/!\ IF YOU WANT PEOPLE TO HELP YOU, PLEASE GIVE AS MUCH DETAIL AS POSSIBLE, INCLUDING THE FULL STACKTRACE AND CODE SNIPPET

Short description
The error during loading of the glue/qqp dataset.

Environment information

• Operating System:

• Python version: Python 3.7.6

• tfds-nightly version: 4.2.0.dev202102090106

• tensorflow version: 2.4.0

• Does the issue still exists with the last tfds-nightly package (pip install --upgrade tfds-nightly) ?
  No.

Reproduction instructions

import tensorflow_datasets as tfds
tfds.load('glue/qqp')

Link to logs

DownloadError Traceback (most recent call last)
in
----> 1 tfds.load('glue/qqp')

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/load.py in load(name, split, data_dir, batch_size, shuffle_files, download, as_supervised, decoders, read_config, with_info, builder_kwargs, download_and_prepare_kwargs, as_dataset_kwargs, try_gcs)
326 if download:
327 download_and_prepare_kwargs = download_and_prepare_kwargs or {}
--> 328 dbuilder.download_and_prepare(**download_and_prepare_kwargs)
329
330 if as_dataset_kwargs is None:

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py in download_and_prepare(self, download_dir, download_config)
450 self._download_and_prepare(
451 dl_manager=dl_manager,
--> 452 download_config=download_config,
453 )
454

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py in _download_and_prepare(self, dl_manager, download_config)
1152 optional_pipeline_kwargs = {}
1153 split_generators = self._split_generators( # pylint: disable=unexpected-keyword-arg
-> 1154 dl_manager, **optional_pipeline_kwargs
1155 )
1156 # TODO(tfds): Could be removed once all datasets are migrated.

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/text/glue.py in _split_generators(self, dl_manager)
447 })
448 else:
--> 449 dl_dir = dl_manager.download_and_extract(self.builder_config.data_url)
450 data_dir = os.path.join(dl_dir, self.builder_config.data_dir)
451 mrpc_files = None

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/download_manager.py in download_and_extract(self, url_or_urls)
635 with self._downloader.tqdm():
636 with self._extractor.tqdm():
--> 637 return _map_promise(self._download_extract, url_or_urls)
638
639 @Property

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/download_manager.py in _map_promise(map_fn, all_inputs)
776 """Map the function into each element and resolve the promise."""
777 all_promises = tf.nest.map_structure(map_fn, all_inputs) # Apply the function
--> 778 res = tf.nest.map_structure(lambda p: p.get(), all_promises) # Wait promises
779 return res

~/envs/t5/lib/python3.7/site-packages/tensorflow/python/util/nest.py in map_structure(func, *structure, **kwargs)
657
658 return pack_sequence_as(
--> 659 structure[0], [func(*x) for x in entries],
660 expand_composites=expand_composites)
661

~/envs/t5/lib/python3.7/site-packages/tensorflow/python/util/nest.py in (.0)
657
658 return pack_sequence_as(
--> 659 structure[0], [func(*x) for x in entries],
660 expand_composites=expand_composites)
661

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/download_manager.py in (p)
776 """Map the function into each element and resolve the promise."""
777 all_promises = tf.nest.map_structure(map_fn, all_inputs) # Apply the function
--> 778 res = tf.nest.map_structure(lambda p: p.get(), all_promises) # Wait promises
779 return res

~/envs/t5/lib/python3.7/site-packages/promise/promise.py in get(self, timeout)
510 target = self._target()
511 self._wait(timeout or DEFAULT_TIMEOUT)
--> 512 return self._target_settled_value(_raise=True)
513
514 def _target_settled_value(self, _raise=False):

~/envs/t5/lib/python3.7/site-packages/promise/promise.py in _target_settled_value(self, _raise)
514 def _target_settled_value(self, _raise=False):
515 # type: (bool) -> Any
--> 516 return self._target()._settled_value(_raise)
517
518 _value = _reason = _target_settled_value

~/envs/t5/lib/python3.7/site-packages/promise/promise.py in _settled_value(self, _raise)
224 if _raise:
225 raise_val = self._fulfillment_handler0
--> 226 reraise(type(raise_val), raise_val, self._traceback)
227 return self._fulfillment_handler0
228

~/envs/t5/lib/python3.7/site-packages/six.py in reraise(tp, value, tb)
701 if value.traceback is not tb:
702 raise value.with_traceback(tb)
--> 703 raise value
704 finally:
705 value = None

~/envs/t5/lib/python3.7/site-packages/promise/promise.py in handle_future_result(future)
842 # type: (Any) -> None
843 try:
--> 844 resolve(future.result())
845 except Exception as e:
846 tb = exc_info()[2]

/cephfs/local/python/3.7.6/lib/python3.7/concurrent/futures/_base.py in result(self, timeout)
426 raise CancelledError()
427 elif self._state == FINISHED:
--> 428 return self.__get_result()
429
430 self._condition.wait(timeout)

/cephfs/local/python/3.7.6/lib/python3.7/concurrent/futures/_base.py in __get_result(self)
382 def __get_result(self):
383 if self._exception:
--> 384 raise self._exception
385 else:
386 return self._result

/cephfs/local/python/3.7.6/lib/python3.7/concurrent/futures/thread.py in run(self)
55
56 try:
---> 57 result = self.fn(*self.args, **self.kwargs)
58 except BaseException as exc:
59 self.future.set_exception(exc)

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/downloader.py in _sync_download(self, url, destination_path, verify)
204 pass
205
--> 206 with _open_url(url, verify=verify) as (response, iter_content):
207 fname = _get_filename(response)
208 path = os.path.join(destination_path, fname)

/cephfs/local/python/3.7.6/lib/python3.7/contextlib.py in enter(self)
110 del self.args, self.kwds, self.func
111 try:
--> 112 return next(self.gen)
113 except StopIteration:
114 raise RuntimeError("generator didn't yield") from None

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/downloader.py in _open_with_requests(url, **kwargs)
266 url = _get_drive_url(url, session)
267 with session.get(url, stream=True, **kwargs) as response:
--> 268 _assert_status(response)
269 yield (response, response.iter_content(chunk_size=io.DEFAULT_BUFFER_SIZE))
270

~/envs/t5/lib/python3.7/site-packages/tensorflow_datasets/core/download/downloader.py in _assert_status(response)
298 if response.status_code != 200:
299 raise DownloadError('Failed to get url {}. HTTP code: {}.'.format(
--> 300 response.url, response.status_code))

DownloadError: Failed to get url https://firebasestorage.googleapis.com/v0/b/mtl-sentence-representations.appspot.com/o/data%2FQQP.zip?alt=media&token=700c6acf-160d-4d89-81d1-de4191d02cb5. HTTP code: 403.

Expected behavior
I expect to download the dataset.

Additional context
The other datasets from the glue are downloaded successfully.