Facing the same problem with Bengali here.
Couldn’t load my previous pretrained models a couple of days back. So I started from scratch. It was working fine till yesterday. Now I’m facing the same problem. The dataset, transforms, splits, model everything is identical. Just running the same code.
RuntimeError: Error(s) in loading state_dict for SequentialRNN:
size mismatch for 0.encoder.weight: copying a param with shape torch.Size([60002, 400]) from checkpoint, the shape in current model is torch.Size([7248, 400]).
size mismatch for 0.encoder_dp.emb.weight: copying a param with shape torch.Size([60002, 400]) from checkpoint, the shape in current model is torch.Size([7248, 400]).
size mismatch for 1.decoder.weight: copying a param with shape torch.Size([60002, 400]) from checkpoint, the shape in current model is torch.Size([7248, 400]).
size mismatch for 1.decoder.bias: copying a param with shape torch.Size([60002]) from checkpoint, the shape in current model is torch.Size([7248]).