Open yuyq96 opened 7 months ago
Hey @yuyq96, I got similar results. Have you resolved the issue?
Hey @yuyq96, I got similar results. Have you resolved the issue?
Unfortunately, I wasn't able to replicate the results on V100 using the official settings, and I don't have access to an A100 either. We've been experimenting with quite different training settings in our model.
Thank you for open sourcing the data and code for UReader. I used
scripts/train_it_v100.sh
to train UReader. However, I was unable to reproduce the benchmark results.Pretrained checkpoint: MAGAer13/mplug-owl-llama-7b
Training loss curve:![train_loss](https://github.com/LukeForeverYoung/UReader/assets/12391727/f4651ded-ff12-4a3c-ba62-b4ccc147b458)
I notice that the micro batch size settings are different on A100 and V100, and it leads to different reduced losses and might affect the training. Other differences between the script and paper include:
linear
instead ofcosine
.11
instead of9
.100*shape_iou+iou
instead ofshape_iou+iou
.@LukeForeverYoung Have you tried completing the training on V100? Could you please verify the loss curve and these results? Thanks!