Hello!
I’m trying to download dataset verbrannter/invoice_dataset_large_cleaned_2 and get DatasetGenerationError: An error occurred while generating the dataset during the Generating train split.
Can you help me?
Regards
Downloading data files: 100%
2/2 [00:00<00:00, 64.17it/s]
Extracting data files: 100%
2/2 [00:00<00:00, 21.97it/s]
Generating train split: 0%
0/25434 [00:00<?, ? examples/s]
FileNotFoundError Traceback (most recent call last)
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\builder.py:1916, in ArrowBasedBuilder._prepare_split_single(self, gen_kwargs, fpath, file_format, max_shard_size, job_id)
1915 try:
→ 1916 writer = writer_class(
1917 features=self.info.features,
1918 path=fpath.replace(“SSSSS”, f"{shard_id:05d}“).replace(“JJJJJ”, f”{job_id:05d}"),
1919 writer_batch_size=self._writer_batch_size,
1920 storage_options=self._fs.storage_options,
1921 embed_local_files=embed_local_files,
1922 )
1923 try:
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\arrow_writer.py:334, in ArrowWriter.init(self, schema, features, path, stream, fingerprint, writer_batch_size, hash_salt, check_duplicates, disable_nullable, update_features, with_metadata, unit, embed_local_files, storage_options)
329 self._path = (
330 fs_token_paths[2][0]
331 if not is_remote_filesystem(self._fs)
332 else self._fs.unstrip_protocol(fs_token_paths[2][0])
333 )
→ 334 self.stream = self._fs.open(fs_token_paths[2][0], “wb”)
335 self._closable_stream = True
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\fsspec\spec.py:1241, in AbstractFileSystem.open(self, path, mode, block_size, cache_options, compression, **kwargs)
1240 ac = kwargs.pop(“autocommit”, not self._intrans)
→ 1241 f = self._open(
1242 path,
1243 mode=mode,
1244 block_size=block_size,
1245 autocommit=ac,
1246 cache_options=cache_options,
1247 **kwargs,
1248 )
1249 if compression is not None:
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\fsspec\implementations\local.py:184, in LocalFileSystem._open(self, path, mode, block_size, **kwargs)
183 self.makedirs(self._parent(path), exist_ok=True)
→ 184 return LocalFileOpener(path, mode, fs=self, **kwargs)
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\fsspec\implementations\local.py:315, in LocalFileOpener.init(self, path, mode, autocommit, fs, compression, **kwargs)
314 self.blocksize = io.DEFAULT_BUFFER_SIZE
→ 315 self._open()
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\fsspec\implementations\local.py:320, in LocalFileOpener._open(self)
319 if self.autocommit or “w” not in self.mode:
→ 320 self.f = open(self.path, mode=self.mode)
321 if self.compression:
FileNotFoundError: [Errno 2] No such file or directory: ‘C:/Users/xllcr/.cache/huggingface/datasets/verbrannter___invoice_dataset_large_cleaned_2/default-b6d7d315edb1e6d7/0.0.0/0111277fb19b16f696664cde7f0cb90f833dec72db2cc73cfdf87e697f78fe02.incomplete/invoice_dataset_large_cleaned_2-train-00000-00000-of-NNNNN.arrow’
The above exception was the direct cause of the following exception:
DatasetGenerationError Traceback (most recent call last)
Cell In [2], line 2
1 from datasets import load_dataset
----> 2 dataset = load_dataset(“verbrannter/invoice_dataset_large_cleaned_2”)
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\load.py:2153, in load_dataset(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, **config_kwargs)
2150 try_from_hf_gcs = path not in _PACKAGED_DATASETS_MODULES
2152 # Download and prepare data
→ 2153 builder_instance.download_and_prepare(
2154 download_config=download_config,
2155 download_mode=download_mode,
2156 verification_mode=verification_mode,
2157 try_from_hf_gcs=try_from_hf_gcs,
2158 num_proc=num_proc,
2159 storage_options=storage_options,
2160 )
2162 # Build dataset for splits
2163 keep_in_memory = (
2164 keep_in_memory if keep_in_memory is not None else is_small_dataset(builder_instance.info.dataset_size)
2165 )
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\builder.py:954, in DatasetBuilder.download_and_prepare(self, output_dir, download_config, download_mode, verification_mode, ignore_verifications, try_from_hf_gcs, dl_manager, base_path, use_auth_token, file_format, max_shard_size, num_proc, storage_options, **download_and_prepare_kwargs)
952 if num_proc is not None:
953 prepare_split_kwargs[“num_proc”] = num_proc
→ 954 self._download_and_prepare(
955 dl_manager=dl_manager,
956 verification_mode=verification_mode,
957 **prepare_split_kwargs,
958 **download_and_prepare_kwargs,
959 )
960 # Sync info
961 self.info.dataset_size = sum(split.num_bytes for split in self.info.splits.values())
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\builder.py:1049, in DatasetBuilder._download_and_prepare(self, dl_manager, verification_mode, **prepare_split_kwargs)
1045 split_dict.add(split_generator.split_info)
1047 try:
1048 # Prepare split will record examples associated to the split
→ 1049 self._prepare_split(split_generator, **prepare_split_kwargs)
1050 except OSError as e:
1051 raise OSError(
1052 "Cannot find data file. "
1053 + (self.manual_download_instructions or “”)
1054 + “\nOriginal error:\n”
1055 + str(e)
1056 ) from None
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\builder.py:1813, in ArrowBasedBuilder._prepare_split(self, split_generator, file_format, num_proc, max_shard_size)
1811 job_id = 0
1812 with pbar:
→ 1813 for job_id, done, content in self._prepare_split_single(
1814 gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
1815 ):
1816 if done:
1817 result = content
File ~\anaconda3\envs\myenv_nlp\lib\site-packages\datasets\builder.py:1958, in ArrowBasedBuilder._prepare_split_single(self, gen_kwargs, fpath, file_format, max_shard_size, job_id)
1956 if isinstance(e, SchemaInferenceError) and e.context is not None:
1957 e = e.context
→ 1958 raise DatasetGenerationError(“An error occurred while generating the dataset”) from e
1960 yield job_id, True, (total_num_examples, total_num_bytes, writer._features, num_shards, shard_lengths)
DatasetGenerationError: An error occurred while generating the dataset