search

NYCU-MAPL / TransTIC

Apache License 2.0
28 stars 4 forks source link

Question about training detail #5

Closed YimChow closed 4 months ago

YimChow commented 4 months ago

Excellent work! I'm attempting to reproduce this research, but I find that some of the training details in the paper are not entirely clear. I was wondering if you could provide information on the training hardware, the number of epochs used, and approximately what the training speed was like (maybe approximate training hours or days)? Thanks a lot! I'm looking forward to your response.

JamesQian1999 commented 4 months ago

We train our models on Nvidia V100 GPUs for approximately 50 epochs, which takes around 2.5 days. The training also works on Nvidia 2080Ti GPUs, taking around 3-4 days.