UNet1DModel not converging on single batch

this is the fix to your exact architecture: UNet1DModel(in_channels = 1, out_channels=1,extra_in_channels=64, down_block_types = (‘DownBlock1DNoSkip’, ‘DownBlock1D’, ‘DownBlock1D’,‘AttnDownBlock1D’,‘DownBlock1D’), up_block_types = (“UpBlock1D”,“UpBlock1D”, “UpBlock1D”, “AttnUpBlock1D”, “UpBlock1DNoSkip”), block_out_channels = (32, 64, 128, 256, 512), time_embedding_type = “fourier”,layers_per_block = 2, act_fn = “silu”) – i opened an issue on this specific quirk on github as well but it was quickly closed, claiming to be a feature and not a bug