Clock parameters (skew and offset) in sensor network are inherently time-varying due to imperfect oscillator circuits. This paper develops a distributed Kalman filter for clock parameters tracking. The proposed algorithm only requires each node to exchange limited information with its direct neighbors, thus is energy efficient, scalable with network size, and is robust to changes in network connectivity. A low-complexity distributed algorithm based on Coordinate-Descent with Bootstrap (CD-BS) is also proposed to provide rapid initialization to the tracking algorithm. Simulation results show that the performance of the proposed distributed tracking algorithm maintains long-term clock parameters accuracy close to the Bayesian Cramer-Rao Lower Bound.