RuntimeError: [enforce fail at CPUAllocator.cpp:68] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 90177536 bytes. Error code 12 (Cannot allocate memor y)

[armitamani]

While running /alpaca_finetuning_v1$ ./finetuning.sh, I am getting error: "RuntimeError: [enforce fail at CPUAllocator.cpp:68] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 90177536 bytes. Error code 12 (Cannot allocate memor
y)
RuntimeError: [enforce fail at CPUAllocator.cpp:68] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 90177536 bytes. Error code 12 (Cannot allocate memor
y)"

I tried to change cpu from gpu in llama_adapter.py code, but then got error: "RuntimeErrorRuntimeError: don't know how to restore data location of torch.BFloat16Storage (tagged with gpu):
don't know how to restore data location of torch.BFloat16Storage (tagged with gpu)"