Closed TinaGioro closed 2 years ago
Hi, these files are generated during inferencing the submit files (the inferenced results), and they will be generated after the training process. Please provide the executive script and the whole training log if any error occurs.
Thanks for replying!
Just now I found the following setting in dee_task.py:
elif self.run_mode == "dueefin_w_tgg":
self.train_file_name = "dueefin_train_w_tgg.json"
self.dev_file_name = "dueefin_dev_w_tgg.json"
self.test_file_name = "dueefin_dev_w_tgg.json"
self.inference_file_name = "dueefin_submit_w_tgg.json"
self.doc_lang = "zh"
So no error will occur. But why you set self.test_file_name = "dueefin_dev_w_tgg.json"? Is it useless?
By setting self.test_file_name = "dueefin_dev_w_tgg.json"
, we could keep the program's logic unchanged across different datasets. Otherwise we have to change the training procedure for those that do not own an official test set.
Agreement
x
to check the agreement items.README.md
.Problem
When I train the code about dueefin, I can't find dueefin_PTPCG_P1R1_wTgg.json file. My question is what the title says. Thanks for reading! Looking forward to your reply!