Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.
I have noticed a potential bug in the calculation of trn_loss and test_loss. The trn_loss is currently computed on the entire train dataset using train_eval_loader. This data loader has a batch size that is 20 times larger than that of trainloader. Consequently, when calculating the trn_loss with the train_eval_loader, it is necessary to use the batch size of train_eval_loader rather than the batch size of trainloader.
Likewise, when calculating the test_loss, we should use the batch size of test_eval_loader instead of the batch size of testloader.
Hello,
I have noticed a potential bug in the calculation of
trn_loss
andtest_loss
. Thetrn_loss
is currently computed on the entire train dataset usingtrain_eval_loader
. This data loader has a batch size that is 20 times larger than that oftrainloader
. Consequently, when calculating thetrn_loss
with thetrain_eval_loader
, it is necessary to use the batch size oftrain_eval_loader
rather than the batch size oftrainloader
.Likewise, when calculating the
test_loss
, we should use the batch size of test_eval_loader instead of the batch size oftestloader
.https://github.com/decile-team/cords/blob/a3d8dc3218e9d80b2b7ab8361c680e3de300905b/train_sl.py#L616
https://github.com/decile-team/cords/blob/a3d8dc3218e9d80b2b7ab8361c680e3de300905b/train_sl.py#L671