C++11 parallel For

I am trying to write a small parallel for loop. However, the output gives me 0 1, 2,3,4,5,6,7,5,4,0,0,0,0,0.. etc I'm testing if it is the way I'm passing iterators, but I'm quite sure. what is a better way to implement a template parallel for loop?

#include <iostream>
#include <iterator>
#include <vector>
#include <thread>
#include <memory>
using namespace std;

template<class InputIterator, class OutputIterator, class Func>
void parallel_for(InputIterator begin, InputIterator end, OutputIterator result, Func func )
{
    unsigned int num_elements = std::distance(begin,end);
    if( (std::thread::hardware_concurrency() == 1) || (std::thread::hardware_concurrency() > num_elements) )
    {
        func(begin,end,result);
    }
    else
    {
      std::vector<std::unique_ptr<std::thread>> tasks;
      const unsigned int num_threads = std::thread::hardware_concurrency();
      unsigned int grp = num_elements / num_threads;
      while( begin != end)
      {
        if( num_elements > grp )
            {
                tasks.push_back(unique_ptr<std::thread>(new std::thread(func, begin, begin + (grp - 1), result)));
                begin += grp;
                num_elements -= grp;
            }
        else
            {
                tasks.push_back(unique_ptr<std::thread>(new std::thread(func, begin, begin + num_elements, result)));
                begin += num_elements;
            }
      }

       for(auto & task : tasks)
        task->join();
    }

}
int main() {
    vector <int> a1= {0,1,2,3,4,5,6,7,5,4,6,7,8,8,5,4,5,6,7,4,5,6,7,8,5,4,6,7,8,9,7,5,4,5,6,7,8,6,5,4,3,33,45,67,100};
    vector<int> a2(45);

    parallel_for(a1.begin(),a1.end(),a2.begin(),[](auto a,auto b, auto c)
    {
        while(a!=b)
        {
            *c = *a;
            ++a;
            ++c;
        }
    });
    for(auto i : a2)
    cout<<i<<"\n";
    return 0;
}