Could you please provide the log for training with the default configuration?

[Jar7]

I train the model with the provided dataset and configuration. And the initial loss is huge, e.g. 8~9e+10. I think there is something wrong with my training. Could you please provide the log for training. Thank you!

[sonack]

Me too, have you found any solution? @Jar7

[dabney777]

I have the same problem loss exaggerate to 4389657512261976064.00 rapidly.

[dabney777]

Use Adam optimizer will get a lower loss but still higher than normal