Loading dataset 'HoangHa/SMILES-250M'... Successfully fetched 84345972 SMILES strings. Starting augmentation and tokenization with 128 worker processes... Processing: 0%| | 0/84345972 [00:00", line 198, in _run_module_as_main File "", line 88, in _run_code File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 101, in main() File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 85, in main with Pool(num_workers, initializer=init_worker, initargs=(CONFIG['TOKENIZER_NAME'], CONFIG['MAX_LENGTH'])) as p: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 739, in __exit__ self.terminate() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 657, in terminate self._terminate() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/util.py", line 227, in __call__ res = self._callback(*self._args, **self._kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 695, in _terminate_pool cls._help_stuff_finish(inqueue, task_handler, len(pool)) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 678, in _help_stuff_finish time.sleep(0) object address : 0x7fb691916560 object refcount : 3 object type : 0x564f994bb2a0 object type name: KeyboardInterrupt object repr : KeyboardInterrupt() lost sys.stderr /home/jovyan/.mlspace/envs/bolgov_simson_training/bin/python: Error while finding module specification for 'create_augmented_dataset.py' (ModuleNotFoundError: __path__ attribute not found on 'create_augmented_dataset' while trying to find 'create_augmented_dataset.py'). Try using 'create_augmented_dataset' instead of 'create_augmented_dataset.py' as the module name. Loading dataset 'HoangHa/SMILES-250M'... Successfully fetched 84345972 SMILES strings. Starting augmentation and tokenization with 128 worker processes... Processing: 0%| | 0/84345972 [00:00", line 198, in _run_module_as_main File "", line 88, in _run_code File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 101, in main() File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 85, in main with Pool(num_workers, initializer=init_worker, initargs=(CONFIG['TOKENIZER_NAME'], CONFIG['MAX_LENGTH'])) as p: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 739, in __exit__ self.terminate() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 657, in terminate self._terminate() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/util.py", line 227, in __call__ res = self._callback(*self._args, **self._kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 695, in _terminate_pool cls._help_stuff_finish(inqueue, task_handler, len(pool)) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 677, in _help_stuff_finish inqueue._reader.recv() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/connection.py", line 250, in recv buf = self._recv_bytes() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/connection.py", line 430, in _recv_bytes buf = self._recv(4) ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/connection.py", line 395, in _recv chunk = read(handle, remaining) ^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Exception ignored in atexit callback: Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/util.py", line 360, in _exit_function Exception in thread Thread-2 (_handle_workers): Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/threading.py", line 1075, in _bootstrap_inner self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/threading.py", line 1012, in run Exception in thread Thread-2 (_handle_workers): Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/threading.py", line 1075, in _bootstrap_inner self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/threading.py", line 1012, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 516, in _handle_workers cls._maintain_pool(ctx, Process, processes, pool, inqueue, File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 340, in _maintain_pool Pool._repopulate_pool_static(ctx, Process, processes, pool, File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 329, in _repopulate_pool_static w.start() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 121, in start self._popen = self._Popen(self) ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/context.py", line 282, in _Popen return Popen(process_obj) ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 19, in __init__ self._launch(process_obj) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 66, in _launch self.pid = os.fork() ^^^^^^^^^ KeyboardInterrupt Fatal Python error: init_threadstate: thread state already initialized Python runtime state: initialized self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 516, in _handle_workers cls._maintain_pool(ctx, Process, processes, pool, inqueue, File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 340, in _maintain_pool Pool._repopulate_pool_static(ctx, Process, processes, pool, File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 329, in _repopulate_pool_static w.start() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 121, in start p.join() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 149, in join self._popen = self._Popen(self) ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/context.py", line 282, in _Popen return Popen(process_obj) ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 19, in __init__ self._launch(process_obj) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 66, in _launch self.pid = os.fork() ^^^^^^^^^ KeyboardInterrupt Fatal Python error: init_threadstate: thread state already initialized Python runtime state: initialized res = self._popen.wait(timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 43, in wait return self.poll(os.WNOHANG if timeout == 0.0 else 0) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/popen_fork.py", line 27, in poll pid, sts = os.waitpid(self.pid, flag) ^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt: Process ForkPoolWorker-182: Process ForkPoolWorker-180: Process ForkPoolWorker-179: Process ForkPoolWorker-183: Process ForkPoolWorker-181: Process ForkPoolWorker-184: Process ForkPoolWorker-186: Process ForkPoolWorker-185: Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 983, in from_pretrained tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 815, in get_tokenizer_config resolved_config_file = cached_file( ^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files hf_hub_download( File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1008, in hf_hub_download return _hf_hub_download_to_cache_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1071, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1533, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1450, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 305, in _request_wrapper return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff response = session.request(method=method, url=url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 983, in from_pretrained tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 815, in get_tokenizer_config resolved_config_file = cached_file( ^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files hf_hub_download( File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1008, in hf_hub_download return _hf_hub_download_to_cache_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1071, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1533, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1450, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff response = session.request(method=method, url=url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 983, in from_pretrained tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 815, in get_tokenizer_config resolved_config_file = cached_file( ^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files hf_hub_download( File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1008, in hf_hub_download return _hf_hub_download_to_cache_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1071, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1533, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1450, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 305, in _request_wrapper return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff response = session.request(method=method, url=url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 983, in from_pretrained tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 815, in get_tokenizer_config resolved_config_file = cached_file( ^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files hf_hub_download( File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1008, in hf_hub_download return _hf_hub_download_to_cache_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1071, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1533, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1450, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 305, in _request_wrapper return _request_wrapper(method=method, url=next_url, follow_relative_redirects=True, **params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff response = session.request(method=method, url=url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 1069, in from_pretrained return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1957, in from_pretrained for template in list_repo_templates( ^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 163, in list_repo_templates for entry in list_repo_tree( ^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 3168, in list_repo_tree for path_info in paginate(path=tree_url, headers=headers, params={"recursive": recursive, "expand": expand}): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_pagination.py", line 36, in paginate r = session.get(path, params=params, headers=headers) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 602, in get return self.request("GET", url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 1069, in from_pretrained return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1877, in from_pretrained if os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 187, in is_remote_url parsed = urlparse(url_or_filename) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/urllib/parse.py", line 401, in urlparse result = ParseResult(scheme, netloc, url, params, query, fragment) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 1, in KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 983, in from_pretrained tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 815, in get_tokenizer_config resolved_config_file = cached_file( ^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files hf_hub_download( File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1008, in hf_hub_download return _hf_hub_download_to_cache_dir( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1071, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) = _get_metadata_or_catch_error( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1533, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 1450, in get_hf_file_metadata r = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 286, in _request_wrapper response = _request_wrapper( ^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/file_download.py", line 309, in _request_wrapper response = http_backoff(method=method, url=url, **params, retry_on_exceptions=(), retry_on_status_codes=(429,)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 310, in http_backoff response = session.request(method=method, url=url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt Traceback (most recent call last): File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/multiprocessing/pool.py", line 109, in worker initializer(*initargs) File "/home/jovyan/simson_training_bolgov/create_augmented_dataset.py", line 35, in init_worker tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py", line 1069, in from_pretrained return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1957, in from_pretrained for template in list_repo_templates( ^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/transformers/utils/hub.py", line 163, in list_repo_templates for entry in list_repo_tree( ^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 3168, in list_repo_tree for path_info in paginate(path=tree_url, headers=headers, params={"recursive": recursive, "expand": expand}): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_pagination.py", line 36, in paginate r = session.get(path, params=params, headers=headers) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 602, in get return self.request("GET", url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 589, in request resp = self.send(prep, **send_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/sessions.py", line 703, in send r = adapter.send(request, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 96, in send return super().send(request, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/requests/adapters.py", line 667, in send resp = conn.urlopen( ^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 787, in urlopen response = self._make_request( ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connectionpool.py", line 534, in _make_request response = conn.getresponse() ^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/site-packages/urllib3/connection.py", line 565, in getresponse httplib_response = super().getresponse() ^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 1430, in getresponse response.begin() File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 331, in begin version, status, reason = self._read_status() ^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/http/client.py", line 292, in _read_status line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/socket.py", line 720, in readinto return self._sock.recv_into(b) ^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1251, in recv_into return self.read(nbytes, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/jovyan/.mlspace/envs/bolgov_simson_training/lib/python3.12/ssl.py", line 1103, in read return self._sslobj.read(len, buffer) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyboardInterrupt