Image-text retrieval results can't be reproduced

Thanks for your contribution!
I run your code and can not reproduce the performance in your paper.
There my results in two different setting：
Finetuning Image-text retrieval with "train-itm-flickr-base-8gpu.json"

Finetuning Image-text retrieval with"train-itm-flickr-base-16gpu-hn.json"

There is a gap between the results and those in your paper. What's the difference between the experiment you do and the code you released? For example, training steps and learning rate. Thanks!

Start by running the two cited configurations, train-itm-flickr-base-8gpu.json and train-itm-flickr-base-16gpu-hn.json, and compare their training steps, learning rate, and reported results with the paper. Check the issue's attached result images and document the experiment differences needed to make the released code reproduce the paper's performance.

Written by the indexing model from the issue text.