Menu

Showing posts with label torchrun is not recognized. Show all posts
Showing posts with label torchrun is not recognized. Show all posts

torchrun is not recognized

Error

torchrun : The term 'torchrun' is not recognized as the name of a cmdlet, function, script file, or operable program. Check                                                             b/ --tokenizer_path tokenizer.model
    + CategoryInfo          : ObjectNotFound: (torchrun:String) [], CommandNotFoundException
    + FullyQualifiedErrorId : CommandNotFoundException
                 torchrun --nproc_per_node 1 example_text_completion.py --ckpt_dir llama-2-7b/ --tokenizer_path tokenizer.modeltorchrun : The term 'torchrun' is not recognized as the name of a cmdlet, function, script file, or operable program. Check    
the spelling of the name, or if a path was included, verify that the path is correct and try again.
At line:1 char:1
+ torchrun --nproc_per_node 1 example_text_completion.py --ckpt_dir lla ...
+ ~~~~~~~~
    + CategoryInfo          : ObjectNotFound: (torchrun:String) [], CommandNotFoundException
    + FullyQualifiedErrorId : CommandNotFoundException


Resolution

Use python -m torch.distributed.run instead of torchrun


References

https://stackoverflow.com/a/72463935/3361311