You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Traceback (most recent call last):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_unix.py", line 43, in _acquire
fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
OSError: [Errno 38] Function not implemented
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/tools/train.py", line 342, in <module>
main()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/tools/train.py", line 338, in main
runner.train()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1728, in train
self._train_loop = self.build_train_loop(
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1520, in build_train_loop
loop = LOOPS.build(
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
obj = obj_cls(**args) # type: ignore
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/engine/runner/loops.py", line 32, in __init__
dataloader = runner.build_dataloader(
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1370, in build_dataloader
dataset = DATASETS.build(dataset_cfg)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
obj = obj_cls(**args) # type: ignore
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/dataset/huggingface.py", line 298, in process_hf_dataset
return process(**kwargs)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/dataset/huggingface.py", line 167, in process
dataset = build_origin_dataset(dataset, split)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/xtuner/dataset/huggingface.py", line 30, in build_origin_dataset
dataset = BUILDER.build(dataset)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
obj = obj_cls(**args) # type: ignore
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/datasets/load.py", line 2556, in load_dataset
builder_instance = load_dataset_builder(
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/datasets/load.py", line 2265, in load_dataset_builder
builder_instance: DatasetBuilder = builder_cls(
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/datasets/builder.py", line 418, in __init__
with FileLock(lock_path):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 297, in __enter__
self.acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 255, in acquire
self._acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_unix.py", line 48, in _acquire
raise NotImplementedError(msg) from exception
NotImplementedError: FileSystem does not appear to support flock; user SoftFileLock instead
Exception ignored in atexit callback: <function matmul_ext_update_autotune_table at 0x7f4f48910790>
Traceback (most recent call last):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 444, in matmul_ext_update_autotune_table
fp16_matmul._update_autotune_table()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 421, in _update_autotune_table
TritonMatmul._update_autotune_table(__class__.__name__ + "_2d_kernel", __class__._2d_kernel)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 150, in _update_autotune_table
cache_manager.put(autotune_table)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 66, in put
with FileLock(self.lock_path):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 297, in __enter__
self.acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 255, in acquire
self._acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_unix.py", line 48, in _acquire
raise NotImplementedError(msg) from exception
NotImplementedError: FileSystem does not appear to support flock; user SoftFileLock instead
Exception ignored in atexit callback: <function matmul_ext_update_autotune_table at 0x7f43efc79750>
Traceback (most recent call last):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 444, in matmul_ext_update_autotune_table
fp16_matmul._update_autotune_table()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 421, in _update_autotune_table
TritonMatmul._update_autotune_table(__class__.__name__ + "_2d_kernel", __class__._2d_kernel)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 150, in _update_autotune_table
cache_manager.put(autotune_table)
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 66, in put
with FileLock(self.lock_path):
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 297, in __enter__
self.acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_api.py", line 255, in acquire
self._acquire()
File "/public/home/xxx/miniconda3/envs/mobilevlm/lib/python3.10/site-packages/filelock/_unix.py", line 48, in _acquire
raise NotImplementedError(msg) from exception
NotImplementedError: FileSystem does not appear to support flock; user SoftFileLock instead.
"看起来您遇到的问题是 fcntl.flock 不被您的文件系统支持。" This explanation comes from GPT4.
The text was updated successfully, but these errors were encountered:
har77774
changed the title
How to solve the following problem with xtuner on Slurn?
How to solve the following problem with xtuner on Slurm?
May 9, 2024
"看起来您遇到的问题是 fcntl.flock 不被您的文件系统支持。" This explanation comes from GPT4.
The text was updated successfully, but these errors were encountered: