fast-bert icon indicating copy to clipboard operation
fast-bert copied to clipboard

Error when using roberta-large-openai-detector for classification

Open saurabh502 opened this issue 4 years ago • 1 comments

Hi , When using roberta-large-openai-detector for multiclass classification , I am getting below error: RuntimeError: Error(s) in loading state_dict for RobertaForSequenceClassification: size mismatch for classifier.out_proj.weight: copying a param with shape torch.Size([2, 1024]) from checkpoint, the shape in current model is torch.Size([4, 1024]). size mismatch for classifier.out_proj.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([4]).

This is working fine when using : roberta-base roberta-large distilroberta-base

saurabh502 avatar Apr 25 '20 03:04 saurabh502

Hi, any update on the issue? Were you able to resolve it??

Ekaanth avatar Jan 29 '22 13:01 Ekaanth