DeepGraphLearning / ULTRA

A foundation model for knowledge graph reasoning
MIT License
478 stars 64 forks source link

Adding batch per epoch option to the finetune script #10

Closed daniel4x closed 10 months ago

daniel4x commented 10 months ago

Allow to specify the batch per epoch in the finetune script (Probably missed it?)

migalkin commented 10 months ago

Thanks, that's a good catch - I was usually running fine-tuning with the run_many script to schedule several repeats with different seeds to get mean/std, but it can work in the single run as well

daniel4x commented 10 months ago

It was a copy-paste mistake 😄 . I also missed the actual slicing from the for loop over the train data so the actual batch_per_epoch is still len(train_loader) as the variable is not used (it was only used for the print).

           # run.py training loop
            for batch in islice(train_loader, batch_per_epoch):
           ....

I'll create another patch for that, wdyt? @migalkin

migalkin commented 10 months ago

Sure, go ahead