loss to convergence

[980202006]

how much the loss when the model convergence

[mimbres]

• It depends. Usually train-loss < 0.3 when setting the Softmax temperature parameter, tau=0.05 (see 640_lamb.yaml).
• With this setup, validation-loss (red) and train-loss (blue) until the 100th epoch:

• On each epoch end, we perform a mini-search-test. Accuracy@1s and @3s would be a useful validation of the model. As in the figure below, the accuracy is about 82.x@1s or 94.x@3s.

[mimbres]

The learning curve is from the pre-trained model in #10 .

[980202006]

thank you!

[mimbres]

The loss and val_acc are updated. Please see #26 (comment)