generalize metric reporting

[gshennvm]

the metric reporting we have is hard coded at various places which caused us to have this grad norm bug 9475e7b. As an example, the code here in grpo.py

RL/nemo_rl/algorithms/grpo.py

Line 1143 in 9475e7b

for k, v in metrics.items():

determines which metric to mean and which to sum, taking the control out of the policy worker's hands. This can cause problems like the grad norm issue. I think a better solution is for the policy worker to tell grpo.py which metric needs to be summed or averaged. Or perhaps average it within the worker itself to avoid the grad norm bug from happening again