Closed josephdviviano closed 9 months ago
Not really harmful. Discrepancies in gpu/cpu/OS I believe. The scripts still run fine on my laptop actually.
To avoid failure, let's add more seeds, and a set a larger epsilon for the gap between obtained result and expected result ?
Seeds added and tolerances increased in https://github.com/GFNOrg/torchgfn/pull/147
I'm not sure if we should actually worry about this (or rather whether this is just due to the seed not being applied to enough RNGs in the scripts -- i.e., we don't seed
numpy
orrandom
).