ValueError: Model 'BertForMaskedLMOptimized' is not supported by the scorer 'RegressionFinetuner'.

[pkuwudi]

Hi there, I'm using community model 'bert-base-chinese' from HuggingFace to finetune masked LMs and I get the following error: ValueError: Model 'BertForMaskedLMOptimized' is not supported by the scorer 'RegressionFinetuner'.

• MLMScorer supports MXNet GluonNLP MLMs: ['bert-base-en-uncased', 'bert-base-en-cased', 'roberta-base-en-cased', 'bert-large-en-uncased', 'bert-large-en-cased', 'roberta-large-en-cased', 'bert-base-en-uncased-owt', 'bert-base-multi-uncased', 'bert-base-multi-cased']
• LMScorer supports MXNet GluonNLP LMs: ['gpt2-117m-en-cased', 'gpt2-345m-en-cased']
• MLMScorerPT supports PyTorch Transformers MLMs:
  • 'albert-*' (wrapped by AlbertForMaskedLMOptimized)
  • 'bert-*' (wrapped by BertForMaskedLMOptimized)
  • 'distilbert-*' (wrapped by DistilBertForMaskedLMOptimized)
  • 'xlm-*' (some variants require 'lang' parameter; XLM-R not supported)

What can I do to solve this issue？ Thanks!

[Helaly96]

did you ever figure it out ?