problem with forword

[Diffelentor]

RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument find_unused_parameters=True to torch.nn.parallel.DistributedDataParallel, and by
making sure all forward function outputs participate in calculating loss.
If you already have done the above, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's forward function. Please include the loss function and the structure of the return value of forward of your module when reporting this issue (e.g. list, dict, iterable).
Parameters which did not receive grad for rank 0: _forward_module.dnn.all_modules.31.Dense_0.bias, _forward_module.dnn.all_modules.31.Dense_0.weight, _forward_module.dnn.all_modules.30.Dense_0.bias, _forward_module.dnn.all_modules.30.Dense_0.weight, _forward_module.dnn.all_modules.29.Dense_0.bias, _forward_module.dnn.all_modules.29.Dense_0.weight, _forward_module.dnn.all_modules.26.Dense_0.bias, _forward_module.dnn.all_modules.26.Dense_0.weight, _forward_module.dnn.all_modules.25.Dense_0.bias, _forward_module.dnn.all_modules.25.Dense_0.weight, _forward_module.dnn.all_modules.24.Dense_0.bias, _forward_module.dnn.all_modules.24.Dense_0.weight, _forward_module.dnn.all_modules.21.Dense_0.bias, _forward_module.dnn.all_modules.21.Dense_0.weight, _forward_module.dnn.all_modules.20.Dense_0.bias, _forward_module.dnn.all_modules.20.Dense_0.weight, _forward_module.dnn.all_modules.19.Dense_0.bias, _forward_module.dnn.all_modules.19.Dense_0.weight, _forward_module.dnn.all_modules.16.Dense_0.bias, _forward_module.dnn.all_modules.16.Dense_0.weight, _forward_module.dnn.all_modules.15.Dense_0.bias, _forward_module.dnn.all_modules.15.Dense_0.weight, _forward_module.dnn.all_modules.14.Dense_0.bias, _forward_module.dnn.all_modules.14.Dense_0.weight, _forward_module.dnn.all_modules.12.Dense_0.bias, _forward_module.dnn.all_modules.12.Dense_0.weight, _forward_module.dnn.all_modules.11.Dense_0.bias, _forward_module.dnn.all_modules.11.Dense_0.weight, _forward_module.dnn.all_modules.9.Dense_0.bias, _forward_module.dnn.all_modules.9.Dense_0.weight, _forward_module.dnn.all_modules.8.Dense_0.bias, _forward_module.dnn.all_modules.8.Dense_0.weight, _forward_module.dnn.all_modules.6.Dense_0.bias, _forward_module.dnn.all_modules.6.Dense_0.weight, _forward_module.dnn.all_modules.5.Dense_0.bias, _forward_module.dnn.all_modules.5.Dense_0.weight, _forward_module.dnn.all_modules.3.Dense_0.bias, _forward_module.dnn.all_modules.3.Dense_0.weight, _forward_module.dnn.all_modules.2.Dense_0.bias, _forward_module.dnn.all_modules.2.Dense_0.weight
Parameter indices which did not receive grad for rank 0: 8 9 18 19 32 33 44 45 58 59 68 69 82 83 92 93 112 113 122 123 134 135 150 151 162 163 174 175 190 191 202 203 214 215 230 231 242 243 254 255