MLPClasiffier produce error when trying to re-fit #7976

Hi,

I am training a MLPClasiffier model twice, each time on a different data-set.
On the second iteration the fit method produce an error. Every time a different error.
I did the processes on various models, this is the only one that produce an error.

this are the errors i get (each time a different one) -

_lbfgsb.error: failed in converting 7th argument `g' of _lbfgsb.setulb to C/Fortran array

ValueError: total size of new array must be unchanged

ValueError: operands could not be broadcast together with shapes (154,100) (25,) (154,100)

thanks