training on vcr task about pevl HOT 4 OPEN

Hi, I fine-tuned it in a larger batch size,(e,g in 32 V100 or 64 A100). You can try a larger gradient_accumulation_steps.

from pevl.

ok, i will try it. thanks

from pevl.

hi, on this weekend i try to run in 16 2080ti with batch size=1 and gradient_accumulation_steps=32.
acc after epoch 0 is 66.7%, epoch 1 is 66.3%.
As the training time is so long and there is no increase after the first two epochs, i want to know whether i should still run, in other words, whether there is something wrong.
or can we frozen some parameters of the model to maintain its performance and speedup the finetune training?

from pevl.

i evaluate the pevl_vcr_finetune.pth and pevl_vcr_ssp.pth, which are provided, on the val set.
Acc of two checkpoints are 74.1/74.8 and 74.2/74.8.
Is it true? There is no improvement and a gap if comparing it with the result in the paper.

from pevl.