zjjJacinthe

How to deal with the error: RuntimeError: value cannot be converted to type float without overflow: (0.000353832,-0.000114967)

1

optimizer.step() File "/opt/conda/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context return func(*args, **kwargs) File "/opt/conda/lib/python3.6/site-packages/torch/optim/sgd.py", line 112, in step p.add_(d_p, alpha=-group['lr']) RuntimeError: value cannot be converted to type float without overflow: (0.000353832,-0.000114967)

use llama

1

I want to replace the gpt-turbo-3.5 model in the code with a llama series model. What do I need to do?