did point loss contributes to total loss?

[Tracyummy]

I found loss_dict_reduced_scaled = {k: v * weight_dict[k] for k, v in loss_dict_reduced.items() if k in weight_dict} the key in weight_dict and loss_dict_reduced is not consistent with each other. one is loss_point, the other is ;oss_points.

[dddddasda]

I found that too, and I fixed it by adopting both loss items.