Open AnddyWang opened 2 years ago
2022-06-24 11:31:30.005 | INFO | processors.processor:get_test_data:75 - len of test data:1602 Traceback (most recent call last): File "test.py", line 476, in main(args) File "test.py", line 442, in main model = MODEL_CLASS[args.model_class].from_pretrained(args.output_path, config=config).to(args.device) File "/usr/local/lib/python3.6/dist-packages/transformers/modeling_utils.py", line 972, in from_pretrained model.class.name, "\n\t".join(error_msgs) RuntimeError: Error(s) in loading state_dict for LEBertCrfForNer: size mismatch for word_embeddings.weight: copying a param with shape torch.Size([29061, 200]) from checkpoint, the shape in current model is torch.Size([29137, 200]).
预测时,报这个异常,有大佬遇到过么
2022-06-24 11:31:30.005 | INFO | processors.processor:get_test_data:75 - len of test data:1602 Traceback (most recent call last): File "test.py", line 476, in main(args) File "test.py", line 442, in main model = MODEL_CLASS[args.model_class].from_pretrained(args.output_path, config=config).to(args.device) File "/usr/local/lib/python3.6/dist-packages/transformers/modeling_utils.py", line 972, in from_pretrained model.class.name, "\n\t".join(error_msgs) RuntimeError: Error(s) in loading state_dict for LEBertCrfForNer: size mismatch for word_embeddings.weight: copying a param with shape torch.Size([29061, 200]) from checkpoint, the shape in current model is torch.Size([29137, 200]).
预测时,报这个异常,有大佬遇到过么
可以看下预测的代码么?
2022-06-24 11:31:30.005 | INFO | processors.processor:get_test_data:75 - len of test data:1602 Traceback (most recent call last): File "test.py", line 476, in
main(args)
File "test.py", line 442, in main
model = MODEL_CLASS[args.model_class].from_pretrained(args.output_path, config=config).to(args.device)
File "/usr/local/lib/python3.6/dist-packages/transformers/modeling_utils.py", line 972, in from_pretrained
model.class.name, "\n\t".join(error_msgs)
RuntimeError: Error(s) in loading state_dict for LEBertCrfForNer:
size mismatch for word_embeddings.weight: copying a param with shape torch.Size([29061, 200]) from checkpoint, the shape in current model is torch.Size([29137, 200]).
预测时,报这个异常,有大佬遇到过么