Challenges in Pre-training with ptp-blip Code: Seeking Advice on Loss Explosion about ptp

[9115jin]

Hi FingerRec,

Thank you for your valuable feedback.

1. I used img2dataset to collect the CC3M images, but it seems that there may have been some mismatch in the file paths, which could have caused the issue.

2. Regarding your feedback, I attempted pre-training solely on the CC3M dataset (3M_corpus.tsv). However, I encountered the same problem of exploding loss. This leads me to believe that there might be an issue with the CC3M dataset I collected. As a result, I am currently in the process of re-collecting the dataset using the CC3M download code provided by FingerRec. I will make sure to share the pre-training results using this dataset with you once it is completed.

[FingerRec]

Hi Jin:

Thanks for you question.

It's hard to find what's the problem because I do not meet this problem with 4M image (one image may have multiple captions for coco and vg) setting, but I guess the file name may not matched.

1. Could you please check if the path of CC3M is the same as ours (since we slightly modify the download code)? If the path not matched, the image may generate wrong captions.
2. If the training is normal with 2.8M Image (2G): CC3M?