Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- root@55cb7f729062:/workspace# ls
- HF_HOME Untitled.ipynb __pycache__ dataset-cache test.py train_notebook_sdxl_mapping_saving.ipynb
- root@55cb7f729062:/workspace# python
- Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
- Type "help", "copyright", "credits" or "license" for more information.
- >>> from multiprocess import set_start_method
- >>> set_start_method("spawn")
- >>> from test import map_train
- <class 'datasets.arrow_dataset.Dataset'>
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- >>> map_train()
- Map (num_proc=2): 0%| | 0/833 [00:00<?, ? examples/s]<class 'datasets.arrow_dataset.Dataset'>
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- 0
- Map (num_proc=2): 0%| | 2/833 [00:21<2:29:09, 10.77s/ examples]0
- 0
- Map (num_proc=2): 1%|▍ | 6/833 [00:21<38:46, 2.81s/ examples]0
- 0
- 0
- Map (num_proc=2): 1%|▊ | 12/833 [00:21<15:05, 1.10s/ examples]0
- 0
- Map (num_proc=2): 2%|█ | 16/833 [00:21<09:37, 1.41 examples/s]0
- 0
- Map (num_proc=2): 2%|█▎ | 20/833 [00:22<06:26, 2.10 examples/s]0
- 0
- Map (num_proc=2): 3%|█▌ | 24/833 [00:22<04:27, 3.03 examples/s]0
- 0
- <class 'datasets.arrow_dataset.Dataset'>
- Map (num_proc=2): 3%|█▊ | 28/833 [00:22<03:09, 4.26 examples/s]0
- 0
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- Map (num_proc=2): 4%|██ | 32/833 [00:22<02:17, 5.81 examples/s]0
- You are using a model of type clip_text_model to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
- 0
- Map (num_proc=2): 4%|██▎ | 36/833 [00:22<01:43, 7.68 examples/s]0
- 0
- Map (num_proc=2): 5%|██▌ | 40/833 [00:22<01:20, 9.81 examples/s]0
- 0
- Map (num_proc=2): 5%|██▊ | 44/833 [00:22<01:04, 12.21 examples/s]0
- 0
- Map (num_proc=2): 6%|███ | 48/833 [00:23<00:56, 13.88 examples/s]0
- 0
- Map (num_proc=2): 6%|███▎ | 52/833 [00:23<00:46, 16.93 examples/s]0
- 0
- Map (num_proc=2): 7%|███▌ | 56/833 [00:23<00:39, 19.65 examples/s]0
- 0
- Map (num_proc=2): 7%|███▊ | 60/833 [00:23<00:34, 22.67 examples/s]0
- 0
- Map (num_proc=2): 8%|████ | 64/833 [00:23<00:32, 23.69 examples/s]0
- 0
- Map (num_proc=2): 8%|████▎ | 68/833 [00:23<00:31, 24.54 examples/s]0
- 0
- Map (num_proc=2): 9%|████▌ | 72/833 [00:24<00:52, 14.40 examples/s]0
- 0
- Map (num_proc=2): 9%|████▊ | 76/833 [00:24<01:09, 10.88 examples/s]0
- 0
- Map (num_proc=2): 10%|█████ | 80/833 [00:25<00:56, 13.38 examples/s]0
- 0
- Map (num_proc=2): 10%|█████▎ | 84/833 [00:25<00:46, 16.02 examples/s]0
- 0
- Map (num_proc=2): 11%|█████▌ | 88/833 [00:25<00:40, 18.25 examples/s]0
- 0
- Map (num_proc=2): 11%|█████▊ | 92/833 [00:25<00:34, 21.25 examples/s]0
- 0
- Map (num_proc=2): 12%|██████ | 96/833 [00:25<00:32, 22.81 examples/s]0
- 0
- Map (num_proc=2): 12%|██████▏ | 100/833 [00:25<00:30, 24.12 examples/s]0
- 0
- Map (num_proc=2): 12%|██████▍ | 104/833 [00:25<00:28, 25.68 examples/s]0
- 0
- Map (num_proc=2): 13%|██████▋ | 108/833 [00:26<00:28, 25.85 examples/s]0
- 0
- Map (num_proc=2): 13%|██████▉ | 112/833 [00:26<00:27, 26.50 examples/s]0
- 0
- Map (num_proc=2): 14%|███████▏ | 116/833 [00:26<00:27, 26.38 examples/s]0
- 0
- Map (num_proc=2): 14%|███████▍ | 120/833 [00:26<00:25, 27.80 examples/s]0
- 0
- Map (num_proc=2): 15%|███████▋ | 124/833 [00:26<00:23, 30.05 examples/s]0
- 0
- Map (num_proc=2): 15%|███████▉ | 128/833 [00:26<00:23, 29.90 examples/s]0
- 0
- Map (num_proc=2): 16%|████████▏ | 132/833 [00:26<00:23, 29.77 examples/s]0
- 0
- Map (num_proc=2): 16%|████████▍ | 136/833 [00:26<00:23, 30.13 examples/s]0
- 0
- Map (num_proc=2): 17%|████████▋ | 140/833 [00:27<00:23, 29.88 examples/s]0
- 0
- Map (num_proc=2): 17%|████████▉ | 144/833 [00:27<00:23, 29.59 examples/s]0
- 0
- Map (num_proc=2): 18%|█████████▏ | 148/833 [00:27<00:22, 30.01 examples/s]0
- 0
- Map (num_proc=2): 18%|█████████▍ | 152/833 [00:27<00:22, 30.00 examples/s]0
- 0
- Map (num_proc=2): 19%|█████████▋ | 156/833 [00:27<00:22, 30.37 examples/s]0
- 0
- Map (num_proc=2): 19%|█████████▉ | 160/833 [00:27<00:21, 31.32 examples/s]0
- 0
- Map (num_proc=2): 20%|██████████▏ | 164/833 [00:27<00:21, 31.32 examples/s]0
- 0
- Map (num_proc=2): 20%|██████████▍ | 168/833 [00:27<00:21, 31.43 examples/s]0
- Process SpawnPoolWorker-1:
- Traceback (most recent call last):
- File "/usr/local/lib/python3.10/dist-packages/multiprocess/process.py", line 314, in _bootstrap
- self.run()
- File "/usr/local/lib/python3.10/dist-packages/multiprocess/process.py", line 108, in run
- self._target(*self._args, **self._kwargs)
- File "/usr/local/lib/python3.10/dist-packages/multiprocess/pool.py", line 114, in worker
- task = get()
- File "/usr/local/lib/python3.10/dist-packages/multiprocess/queues.py", line 370, in get
- return _ForkingPickler.loads(res)
- File "/usr/local/lib/python3.10/dist-packages/dill/_dill.py", line 301, in loads
- return load(file, ignore, **kwds)
- File "/usr/local/lib/python3.10/dist-packages/dill/_dill.py", line 287, in load
- return Unpickler(file, ignore=ignore, **kwds).load()
- File "/usr/local/lib/python3.10/dist-packages/dill/_dill.py", line 442, in load
- obj = StockUnpickler.load(self)
- File "/usr/local/lib/python3.10/dist-packages/torch/storage.py", line 337, in _load_from_bytes
- return torch.load(io.BytesIO(b))
- File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1028, in load
- return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
- File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1256, in _legacy_load
- result = unpickler.load()
- File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1193, in persistent_load
- wrap_storage=restore_location(obj, location),
- File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 381, in default_restore_location
- result = fn(storage, location)
- File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 277, in _cuda_deserialize
- return torch.UntypedStorage(obj.nbytes(), device=torch.device(location))
- torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacty of 15.73 GiB of which 14.25 MiB is free. Process 195904 has 3.73 GiB memory in use. Process 196147 has 6.99 GiB memory in use. Process 196146 has 4.98 GiB memory in use. Of the allocated memory 4.66 GiB is allocated by PyTorch, and 172.25 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF
- 0
- Map (num_proc=2): 21%|██████████▋ | 172/833 [00:28<00:20, 32.04 examples/s]0
- 0
- Map (num_proc=2): 21%|██████████▉ | 176/833 [00:28<00:21, 30.91 examples/s]0
- 0
- Map (num_proc=2): 22%|███████████▏ | 180/833 [00:28<00:21, 30.50 examples/s]0
- 0
- Map (num_proc=2): 22%|███████████▍ | 184/833 [00:28<00:21, 29.98 examples/s]0
- 0
- Map (num_proc=2): 23%|███████████▋ | 188/833 [00:28<00:21, 29.40 examples/s]0
- 0
- Map (num_proc=2): 23%|███████████▉ | 192/833 [00:28<00:21, 29.24 examples/s]0
- 0
- Map (num_proc=2): 24%|████████████▏ | 196/833 [00:28<00:21, 29.00 examples/s]0
- 0
- Map (num_proc=2): 24%|████████████▍ | 200/833 [00:29<00:21, 29.30 examples/s]0
- 0
- Map (num_proc=2): 24%|████████████▋ | 204/833 [00:29<00:21, 29.88 examples/s]0
- 0
- Map (num_proc=2): 25%|████████████▉ | 208/833 [00:29<00:20, 30.95 examples/s]0
- 0
- Map (num_proc=2): 25%|█████████████ | 210/833 [00:29<01:27, 7.13 examples/s]
- Traceback (most recent call last):
- File "<stdin>", line 1, in <module>
- File "/workspace/test.py", line 222, in map_train
- return train_dataset.map(compute_embeddings_fn, batched=True, batch_size=2, with_rank=True, num_proc=2)
- File "/usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py", line 592, in wrapper
- out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
- File "/usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py", line 557, in wrapper
- out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
- File "/usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py", line 3185, in map
- for rank, done, content in iflatmap_unordered(
- File "/usr/local/lib/python3.10/dist-packages/datasets/utils/py_utils.py", line 647, in iflatmap_unordered
- raise RuntimeError(
- RuntimeError: One of the subprocesses has abruptly died during map operation.To debug the error, disable multiprocessing.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement