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 "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Traceback (most recent call last):
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Traceback (most recent call last):
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Traceback (most recent call last):
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Traceback (most recent call last):
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Traceback (most recent call last):
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 478, in<module>main()
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/dist_clm_train.py", line 397, in main
init_communicators(args)
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/comm_utils.py", line 103, in init_communicators
_PIPELINE_PARALLEL_COMM = NCCLCommunicator(_PIPELINE_PARALLEL_RANK, args.cuda_id, args.pipeline_group_size,
File "/mnt/camelot/Team4/fall23/llama2/Book/OpenChatKit-main/training/comm/nccl_backend.py", line 31, in __init__
cupy.cuda.Device(cuda_id).use()
File "cupy/cuda/device.pyx", line 192, in cupy.cuda.device.Device.use
File "cupy/cuda/device.pyx", line 198, in cupy.cuda.device.Device.use
File "cupy_backends/cuda/api/runtime.pyx", line 375, in cupy_backends.cuda.api.runtime.setDevice
File "cupy_backends/cuda/api/runtime.pyx", line 144, in cupy_backends.cuda.api.runtime.check_status
cupy_backends.cuda.api.runtime.CUDARuntimeError: cudaErrorInvalidDevice: invalid device ordinal
Activity
orangetin commentedon Nov 2, 2023
File output