the final mle estimates are :

                 coefficient     standard-error    t-ratio（t值）
  beta 0         0.72235820E+04  0.40841114E+02  0.17687035E+03
  beta 1        -0.44391110E+03  0.17298345E+03 -0.25662056E+01
  beta 2        -0.10589797E+04  0.18334136E+03 -0.57760003E+01
  sigma-squared  0.12632578E+07  0.10000007E+01  0.12632569E+07
  gamma          0.18714592E-01  0.46892938E+00  0.39909190E-01
   mu is restricted to be zero
   eta is restricted to be zero

log likelihood function =  -0.67420718E+02

the likelihood value is less than that obtained
using ols! - try again using different starting values