sudarshan babu comments

Results 14 comments of


                                            sudarshan babu

why is it that using the pre-training model you provided, without any changes in the code, the test results vary greatly, even up to 10 point fluctuations？

One more question: are the standard deviations mentioned in the paper calculated from 3 different runs or are they calculated from the 600 test tasks within a run ? Thank...

why is it that using the pre-training model you provided, without any changes in the code, the test results vary greatly, even up to 10 point fluctuations?

Yeah I seem to have gotten similar results 100%|█████████████████████████████████████████████████████████████████████████████████████████| 600/600 [10:13

Training time for QM9 dataset

Thank you for your work!!!

Training time for QM9 dataset

I fixed some package issues and now it is taking me 500 seconds per epoch, is this standard?