Closed laleye closed 3 years ago
I'm sorry that there may be a bug in my code, but I can't help you locate the error。 You can try run_span_ner.py, which should work better than run_crf_ner.py
Thanks for your response. By using run_span_ner, I was able to run an exp after fixing a small bug on line 232: adv.adversarial_training(args, inputs, optimizer) insted of adv.training(args, inputs, optimizer). I can do a pull request if you don't have time to correct it and if I have the rights.
has this issue been solved by now?
I got this error while evaluting model after the first epoch. I'm using the roberta+crf with the script run_crf_ner.py.
File "token_classification/roberta_train.py", line 336, in evaluate preds_list[i].append(label_map[preds[i][j]]) KeyError: -1
If someone has already encountered this error, please help to understand why since my label ids don't contain -1 value.