A little question about the training

[ilingen]

Hi, thank u for your excellent work. Please forgive me for asking a simple question.
These days, I am training a unsup-bert model. I set random seed=0 and get a standard result with avg score 78.54, which is same as the paper reported (78.54±0.15), both the results are lower than your provided model (78.87).
So I wonder if you have updated the training strategy or provide the best model for us.

[kongds]

Thank you for your interest in our work.

We provide our best checkpoint from 10 random runs for unsupervised settings . And we also report the best and worst performance of 10 random runs in paper Section 6.2.

[ilingen]

Thanks for your reply. I am going to close the issue.