Synchronization: the problem, part 3

The second time I ran it on the same VM it appeared to be caught in an infinite loop. The output looked like this:

1
3
4
5
6
7
8
9
10
11
...
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
...
342
343
344
345

I didn't run it long enough to be sure, but my best guess is that it would have continued to run until it wrapped around into the negative numbers, then counted back up to 100, and then stopped.