PromDA icon indicating copy to clipboard operation
PromDA copied to clipboard

Published 20 hours ago • verified publisher icon GaryYufei

Question about SenLabel

Open wpwpwpyo opened this issue 2 years ago • 4 comments

Sorry to bother you .I have some question about running to script/run_few_shot_bert_prefix_sen_cls.sh at line 61,the train_SenLabel.py will raise "IndexError: list index out of range" at line 162.I check the detail and find that "test_data = SenLabelDataset(_C, _C.test_path, label_dict, tokenizer)" prints "Total instances 0"(But the line 154 "dev_data = SenLabelDataset(_C, _C.dev_path, label_dict, tokenizer)" works well,it prints "Total instances 960")

wpwpwpyo avatar Apr 14 '22 15:04 wpwpwpyo

Sorry to bother you .I have some question about running to script/run_few_shot_bert_prefix_sen_cls.sh at line 61,the train_SenLabel.py will raise "IndexError: list index out of range" at line 162.I check the detail and find that "test_data = SenLabelDataset(_C, _C.test_path, label_dict, tokenizer)" prints "Total instances 0"(But the line 154 "dev_data = SenLabelDataset(_C, _C.dev_path, label_dict, tokenizer)" works well,it prints "Total instances 960")

Hi, I have the same problem. You can try modifying line 75 of train_data_augmentation.py ( label = words[0].lower() ).

Chaiyut1002 avatar Apr 15 '22 05:04 Chaiyut1002

Sorry to bother you .I have some question about running to script/run_few_shot_bert_prefix_sen_cls.sh at line 61,the train_SenLabel.py will raise "IndexError: list index out of range" at line 162.I check the detail and find that "test_data = SenLabelDataset(_C, _C.test_path, label_dict, tokenizer)" prints "Total instances 0"(But the line 154 "dev_data = SenLabelDataset(_C, _C.dev_path, label_dict, tokenizer)" works well,it prints "Total instances 960")

Can I have your training log and have a look?

GaryYufei avatar Apr 15 '22 07:04 GaryYufei

Sorry to bother you .I have some question about running to script/run_few_shot_bert_prefix_sen_cls.sh at line 61,the train_SenLabel.py will raise "IndexError: list index out of range" at line 162.I check the detail and find that "test_data = SenLabelDataset(_C, _C.test_path, label_dict, tokenizer)" prints "Total instances 0"(But the line 154 "dev_data = SenLabelDataset(_C, _C.dev_path, label_dict, tokenizer)" works well,it prints "Total instances 960")

Can I have your training log and have a look?

图片

wpwpwpyo avatar Apr 16 '22 03:04 wpwpwpyo

Hi @wpwpwpyo, Could you try to run the code again? I have fixed the issue -- Due to a small bug, the output view prompt is never trained. So it produces wired outputs. I believe the current version should solve the problem

GaryYufei avatar Apr 16 '22 17:04 GaryYufei