Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details. bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt: 0%| | 0.00/22.2G [00:00 sys.exit(main()) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/commands/huggingface_cli.py", line 52, in main service.run() File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/commands/upload.py", line 191, in run print(self._upload()) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/commands/upload.py", line 286, in _upload return self.api.upload_folder( File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_api.py", line 1398, in _inner return fn(self, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_api.py", line 4857, in upload_folder commit_info = self.create_commit( File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_api.py", line 1398, in _inner return fn(self, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_api.py", line 3770, in create_commit self.preupload_lfs_files( File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/hf_api.py", line 4317, in preupload_lfs_files _upload_lfs_files( File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/_commit_api.py", line 446, in _upload_lfs_files thread_map( File "/usr/local/lib/python3.10/dist-packages/tqdm/contrib/concurrent.py", line 69, in thread_map return _executor_map(ThreadPoolExecutor, fn, *iterables, **tqdm_kwargs) File "/usr/local/lib/python3.10/dist-packages/tqdm/contrib/concurrent.py", line 49, in _executor_map with PoolExecutor(max_workers=max_workers, initializer=tqdm_class.set_lock, File "/usr/lib/python3.10/concurrent/futures/_base.py", line 649, in __exit__ self.shutdown(wait=True) File "/usr/lib/python3.10/concurrent/futures/thread.py", line 235, in shutdown t.join() File "/usr/lib/python3.10/threading.py", line 1096, in join self._wait_for_tstate_lock() File "/usr/lib/python3.10/threading.py", line 1116, in _wait_for_tstate_lock if lock.acquire(block, timeout): KeyboardInterrupt bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt: 23%|██▎ | 5.13G/22.2G [10:04<20:55, 13.6MB/s] bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt: 25%|██▌ | 5.55G/22.2G [10:04<20:32, 13.5MB/s] bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt: 17%|█▋ | 3.72G/22.2G [10:04<59:14, 5.19MB/s]  bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt: 23%|██▎ | 5.18G/22.2G [10:04<28:00, 10.1MB/s] bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt: 23%|██▎ | 5.13G/22.2G [10:04<21:08, 13.4MB/s] bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt: 33%|███▎ | 7.39G/22.2G [10:04<22:17, 11.0MB/s] bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt: 23%|██▎ | 5.18G/22.2G [10:04<27:48, 10.2MB/s]Exception ignored in: Traceback (most recent call last): File "/usr/lib/python3.10/threading.py", line 1537, in _shutdown atexit_call() File "/usr/lib/python3.10/concurrent/futures/thread.py", line 31, in _python_exit t.join() File "/usr/lib/python3.10/threading.py", line 1096, in join self._wait_for_tstate_lock() File "/usr/lib/python3.10/threading.py", line 1116, in _wait_for_tstate_lock if lock.acquire(block, timeout): KeyboardInterrupt: