Cannot Assign Requested Address

I want to reproduce the ZINC pretrain. However, I meet the problem with the log:
Traceback (most recent call last):
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 1350, in do_open
encode_chunked=req.has_header('Transfer-encoding'))
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 1281, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 1327, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 1276, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 1036, in _send_output
self.send(msg)
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 976, in send
self.connect()
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 1443, in connect
super().connect()
File "/opt/conda/envs/graphormer-env/lib/python3.7/http/client.py", line 948, in connect
(self.host,self.port), self.timeout, self.source_address)
File "/opt/conda/envs/graphormer-env/lib/python3.7/socket.py", line 728, in create_connection
raise err
File "/opt/conda/envs/graphormer-env/lib/python3.7/socket.py", line 716, in create_connection
sock.connect(sa)
OSError: [Errno 99] Cannot assign requested address

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/conda/envs/graphormer-env/bin/fairseq-train", line 8, in
sys.exit(cli_main())
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/fairseq_cli/train.py", line 557, in cli_main
distributed_utils.call_main(cfg, main)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/fairseq/distributed/utils.py", line 369, in call_main
main(cfg, **kwargs)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/fairseq_cli/train.py", line 87, in main
task = tasks.setup_task(cfg.task)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/fairseq/tasks/init.py", line 46, in setup_task
return task.setup_task(cfg, **kwargs)
File "//graphormer-env-docker/Graphormer/graphormer/tasks/graph_prediction.py", line 179, in setup_task
return cls(cfg)
File "//graphormer-env-docker/Graphormer/graphormer/tasks/graph_prediction.py", line 158, in init
seed=cfg.seed,
File "//graphormer-env-docker/Graphormer/graphormer/data/dataset.py", line 84, in init
self.dataset = PYGDatasetLookupTable.GetPYGDataset(dataset_spec, seed=seed)
File "//graphormer-env-docker/Graphormer/graphormer/data/pyg_datasets/pyg_dataset_lookup_table.py", line 90, in GetPYGDataset
inner_dataset = MyZINC(root=root)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/datasets/zinc.py", line 54, in init
super(ZINC, self).init(root, transform, pre_transform, pre_filter)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/data/in_memory_dataset.py", line 60, in init
super().init(root, transform, pre_transform, pre_filter)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 83, in init
self._download()
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 140, in _download
self.download()
File "/~/graphormer-env-docker/Graphormer/graphormer/data/pyg_datasets/pyg_dataset_lookup_table.py", line 41, in download
super(MyZINC, self).download()
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/datasets/zinc.py", line 76, in download
path = download_url(self.url, self.root)
File "/opt/conda/envs/graphormer-env/lib/python3.7/site-packages/torch_geometric/data/download.py", line 34, in download_url
data = urllib.request.urlopen(url, context=context)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 525, in open
response = self._open(req, data)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 543, in _open
'_open', req)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 503, in _call_chain
result = func(*args)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 1393, in https_open
context=self._context, check_hostname=self._check_hostname)
File "/opt/conda/envs/graphormer-env/lib/python3.7/urllib/request.py", line 1352, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [Errno 99] Cannot assign requested address>

I understand that it might due to my network problem. But how can I run the code without network.

The failure occurs during MyZINC dataset setup in graphormer/data/pyg_datasets/pyg_dataset_lookup_table.py, reached from graphormer/tasks/graph_prediction.py and fairseq-train. Start by tracing the ZINC download path and determine how the dataset is expected to be supplied when network access is unavailable. Done means ZINC pretraining can start offline, or the supported limitation and workaround are documented.