Post
76
we taught a small model to predict how simulated fluid would move eight steps into the future. it learned from examples, then succeeded on examples withheld from training.
two things mattered:
- its memory helped. the version with an internal memory produced about 41–45% less prediction error than the comparison model using recent observations.
- the learning was repeatable. restarting training reproduced every recorded update and saved checkpoint exactly. resuming halfway through also produced the same ending.
that gives us working evidence that bf16 gpu training can learn and remain exactly repeatable on this 3090 ti and software setup.
thank you for your time.
two things mattered:
- its memory helped. the version with an internal memory produced about 41–45% less prediction error than the comparison model using recent observations.
- the learning was repeatable. restarting training reproduced every recorded update and saved checkpoint exactly. resuming halfway through also produced the same ending.
that gives us working evidence that bf16 gpu training can learn and remain exactly repeatable on this 3090 ti and software setup.
thank you for your time.
