Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Input sent2 #7

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Input sent2 #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d1afc34
[Modified] ocr_tagging model First Commit
KHUjsLee May 24, 2024
7439307
[MODIFIED] input sentence-> CLS + IDS + SEP + IDS + SEP
KHUjsLee May 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
238 changes: 238 additions & 0 deletions ocr_tagging/ckpt_ocr/model/train.log
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,3 +144,241 @@ I-
2024-05-11 22:00:59;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/config.json HTTP/1.1" 200 0
2024-05-11 22:01:00;[INFO];>>>>>>> Training Start!
2024-05-11 22:01:00;[INFO];[Now Epoch: 0]
2024-05-24 20:11:24;[INFO];[���� ���ɾ�]: sh ./scripts_ocr/model/do_train.sh
2024-05-24 20:11:24;[INFO];[Config]
2024-05-24 20:11:24;[INFO];{'epochs': 10, 'train_batch_size': 4, 'valid_batch_size': 4, 'init_model_path': 'klue/bert-base', 'max_length': 512, 'need_birnn': 0, 'aspect_drop_ratio': 0.3, 'aspect_in_feature': 768, 'stop_patience': 3, 'train_fp': './resources_ocr/parsing_data/train/', 'valid_fp': './resources_ocr/parsing_data/valid/', 'base_path': './ckpt_ocr/model/', 'label_info_file': 'meta.bin', 'out_model_path': 'pytorch_model.bin', 'cmd': 'sh ./scripts_ocr/model/do_train.sh'}
2024-05-24 20:11:24;[INFO];>>>>>>> Device Setting
2024-05-24 20:11:24;[INFO];Now using CPU
2024-05-24 20:11:24;[INFO];>>>>>>> Now setting Aspect Category Encoder
2024-05-24 20:11:24;[INFO];>>>>>>> Now setting train/valid DataLoaders
2024-05-24 20:11:24;[DEBUG];Starting new HTTPS connection (1): huggingface.co:443
2024-05-24 20:11:25;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-24 20:11:25;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-24 20:11:25;[INFO];>>>>>>> Now setting Model Architecture
2024-05-24 20:11:25;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/config.json HTTP/1.1" 200 0
2024-05-24 20:11:27;[INFO];>>>>>>> Training Start!
2024-05-24 20:11:27;[INFO];[Now Epoch: 0]
2024-05-24 20:33:24;[INFO];*****eval metrics*****
2024-05-24 20:33:24;[INFO];eval_loss: 68.64664435386658
2024-05-24 20:33:24;[INFO];eval_runtime: 0:00:56.789281
2024-05-24 20:33:24;[INFO];eval_samples: 8
2024-05-24 20:33:24;[INFO];eval_samples_per_second: 0:00:07.098660
2024-05-24 20:33:24;[INFO];Aspect Accuracy: 0.57
2024-05-24 20:33:24;[INFO];Aspect f1score micro : 0.57
2024-05-24 20:33:24;[INFO];Aspect Accuracy Report:
2024-05-24 20:33:24;[INFO]; precision recall f1-score support

B-�������� 0.0000 0.0000 0.0000 9
B-���������� 0.0000 0.0000 0.0000 1
B-�������� 0.0000 0.0000 0.0000 1
B-��Ƽ��Ʈ 0.0000 0.0000 0.0000 4
B-���� 0.0000 0.0000 0.0000 2
B-�ܷ�ǥ�� 0.0000 0.0000 0.0000 2
B-���� 0.0000 0.0000 0.0000 2
B-���̽� 0.0000 0.0000 0.0000 2
B-�޴뼺 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 19
I-���������� 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 2
I-��Ƽ��Ʈ 0.0000 0.0000 0.0000 11
I-���� 0.0000 0.0000 0.0000 9
I-�ܷ�ǥ�� 0.0000 0.0000 0.0000 4
I-���� 0.0000 0.0000 0.0000 32
I-���̽� 0.0000 0.0000 0.0000 2
I-�޴뼺 0.0000 0.0000 0.0000 4
O 0.7556 1.0000 0.8608 340

accuracy 0.7556 450
macro avg 0.0398 0.0526 0.0453 450
weighted avg 0.5709 0.7556 0.6504 450

2024-05-24 20:33:24;[INFO];Train Loss = 97.60242123901844 Valid Loss = 68.64664435386658
2024-05-24 20:33:26;[INFO];[Now Epoch: 1]
2024-05-24 20:54:45;[INFO];*****eval metrics*****
2024-05-24 20:54:45;[INFO];eval_loss: 61.73322319984436
2024-05-24 20:54:45;[INFO];eval_runtime: 0:00:53.207835
2024-05-24 20:54:45;[INFO];eval_samples: 8
2024-05-24 20:54:45;[INFO];eval_samples_per_second: 0:00:06.650979
2024-05-24 20:54:45;[INFO];Aspect Accuracy: 0.56
2024-05-24 20:54:45;[INFO];Aspect f1score micro : 0.56
2024-05-24 20:54:45;[INFO];Aspect Accuracy Report:
2024-05-24 20:54:45;[INFO]; precision recall f1-score support

B-�������� 0.0000 0.0000 0.0000 9
B-���������� 0.0000 0.0000 0.0000 1
B-�������� 0.0000 0.0000 0.0000 1
B-��Ƽ��Ʈ 0.0000 0.0000 0.0000 4
B-���� 0.0000 0.0000 0.0000 2
B-�ܷ�ǥ�� 0.0000 0.0000 0.0000 2
B-���� 0.0000 0.0000 0.0000 2
B-���̽� 0.0000 0.0000 0.0000 2
B-�޴뼺 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 19
I-���������� 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 2
I-��Ƽ��Ʈ 0.0000 0.0000 0.0000 11
I-���͸������ӵ� 0.0000 0.0000 0.0000 0
I-���� 0.0000 0.0000 0.0000 9
I-�ܷ�ǥ�� 0.0000 0.0000 0.0000 4
I-���� 0.0000 0.0000 0.0000 32
I-���̽� 0.0000 0.0000 0.0000 2
I-�޴뼺 0.0000 0.0000 0.0000 4
O 0.7539 0.9912 0.8564 340

accuracy 0.7489 450
macro avg 0.0377 0.0496 0.0428 450
weighted avg 0.5696 0.7489 0.6471 450

2024-05-24 20:54:45;[INFO];Train Loss = 73.78356349468231 Valid Loss = 61.73322319984436
2024-05-24 20:54:46;[INFO];[Now Epoch: 2]
2024-05-24 21:13:25;[INFO];*****eval metrics*****
2024-05-24 21:13:25;[INFO];eval_loss: 59.49133384227753
2024-05-24 21:13:25;[INFO];eval_runtime: 0:01:01.399662
2024-05-24 21:13:25;[INFO];eval_samples: 8
2024-05-24 21:13:25;[INFO];eval_samples_per_second: 0:00:07.674958
2024-05-24 21:13:25;[INFO];Aspect Accuracy: 0.56
2024-05-24 21:13:25;[INFO];Aspect f1score micro : 0.56
2024-05-24 21:13:25;[INFO];Aspect Accuracy Report:
2024-05-24 21:13:25;[INFO]; precision recall f1-score support

B-�������� 0.0000 0.0000 0.0000 9
B-���������� 0.0000 0.0000 0.0000 1
B-�������� 0.0000 0.0000 0.0000 1
B-��Ƽ��Ʈ 0.0000 0.0000 0.0000 4
B-���� 0.0000 0.0000 0.0000 2
B-�ܷ�ǥ�� 0.0000 0.0000 0.0000 2
B-���� 0.0000 0.0000 0.0000 2
B-���̽� 0.0000 0.0000 0.0000 2
B-�޴뼺 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 19
I-���������� 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 2
I-��Ƽ��Ʈ 0.0000 0.0000 0.0000 11
I-���͸������ӵ� 0.0000 0.0000 0.0000 0
I-���� 0.0000 0.0000 0.0000 9
I-�ܷ�ǥ�� 0.0000 0.0000 0.0000 4
I-���� 0.0000 0.0000 0.0000 32
I-���̽� 0.0000 0.0000 0.0000 2
I-�޴뼺 0.0000 0.0000 0.0000 4
O 0.7607 0.9912 0.8608 340

accuracy 0.7489 450
macro avg 0.0380 0.0496 0.0430 450
weighted avg 0.5748 0.7489 0.6504 450

2024-05-24 21:13:25;[INFO];Train Loss = 63.223463617265224 Valid Loss = 59.49133384227753
2024-05-24 21:13:26;[INFO];[Now Epoch: 3]
2024-05-27 16:26:06;[INFO];[���� ���ɾ�]: sh ./scripts_ocr/model/do_train.sh
2024-05-27 16:26:06;[INFO];[Config]
2024-05-27 16:26:06;[INFO];{'epochs': 10, 'train_batch_size': 4, 'valid_batch_size': 4, 'init_model_path': 'klue/bert-base', 'max_length': 512, 'need_birnn': 0, 'aspect_drop_ratio': 0.3, 'aspect_in_feature': 768, 'stop_patience': 3, 'train_fp': './resources_ocr/parsing_data/train/', 'valid_fp': './resources_ocr/parsing_data/valid/', 'base_path': './ckpt_ocr/model/', 'label_info_file': 'meta.bin', 'out_model_path': 'pytorch_model.bin', 'cmd': 'sh ./scripts_ocr/model/do_train.sh'}
2024-05-27 16:26:06;[INFO];>>>>>>> Device Setting
2024-05-27 16:26:06;[INFO];Now using CPU
2024-05-27 16:26:06;[INFO];>>>>>>> Now setting Aspect Category Encoder
2024-05-27 16:26:06;[INFO];>>>>>>> Now setting train/valid DataLoaders
2024-05-27 16:26:06;[DEBUG];Starting new HTTPS connection (1): huggingface.co:443
2024-05-27 16:26:06;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 16:26:07;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 16:26:07;[INFO];>>>>>>> Now setting Model Architecture
2024-05-27 16:26:07;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/config.json HTTP/1.1" 200 0
2024-05-27 16:26:09;[INFO];>>>>>>> Training Start!
2024-05-27 16:26:09;[INFO];[Now Epoch: 0]
2024-05-27 19:33:48;[INFO];[���� ���ɾ�]: sh ./scripts_ocr/model/do_train.sh
2024-05-27 19:33:48;[INFO];[Config]
2024-05-27 19:33:48;[INFO];{'epochs': 10, 'train_batch_size': 4, 'valid_batch_size': 4, 'init_model_path': 'klue/bert-base', 'max_length': 512, 'need_birnn': 0, 'aspect_drop_ratio': 0.3, 'aspect_in_feature': 768, 'stop_patience': 3, 'train_fp': './resources_ocr/parsing_data/train/', 'valid_fp': './resources_ocr/parsing_data/valid/', 'base_path': './ckpt_ocr/model/', 'label_info_file': 'meta.bin', 'out_model_path': 'pytorch_model.bin', 'cmd': 'sh ./scripts_ocr/model/do_train.sh'}
2024-05-27 19:33:48;[INFO];>>>>>>> Device Setting
2024-05-27 19:33:48;[INFO];Now using CPU
2024-05-27 19:33:48;[INFO];>>>>>>> Now setting Aspect Category Encoder
2024-05-27 19:33:48;[INFO];>>>>>>> Now setting train/valid DataLoaders
2024-05-27 19:33:48;[DEBUG];Starting new HTTPS connection (1): huggingface.co:443
2024-05-27 19:33:48;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 19:33:49;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 19:33:49;[INFO];>>>>>>> Now setting Model Architecture
2024-05-27 19:33:49;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/config.json HTTP/1.1" 200 0
2024-05-27 19:33:50;[INFO];>>>>>>> Training Start!
2024-05-27 19:33:50;[INFO];[Now Epoch: 0]
2024-05-27 19:47:32;[INFO];*****eval metrics*****
2024-05-27 19:47:32;[INFO];eval_loss: 49.402870178222656
2024-05-27 19:47:32;[INFO];eval_runtime: 0:00:45.805668
2024-05-27 19:47:32;[INFO];eval_samples: 8
2024-05-27 19:47:32;[INFO];eval_samples_per_second: 0:00:05.725708
2024-05-27 19:47:32;[INFO];Aspect Accuracy: 0.55
2024-05-27 19:47:32;[INFO];Aspect f1score micro : 0.55
2024-05-27 19:47:32;[INFO];Aspect Accuracy Report:
2024-05-27 19:47:32;[INFO]; precision recall f1-score support

B-�������� 0.0000 0.0000 0.0000 11
B-���������� 0.0000 0.0000 0.0000 1
B-�������� 0.0000 0.0000 0.0000 1
B-��Ƽ��Ʈ 0.0000 0.0000 0.0000 4
B-���� 0.0000 0.0000 0.0000 2
B-�ܷ�ǥ�� 0.0000 0.0000 0.0000 2
B-���� 0.0000 0.0000 0.0000 2
B-���̽� 0.0000 0.0000 0.0000 2
B-�޴뼺 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 8
I-���������� 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 2
I-��Ƽ��Ʈ 0.0000 0.0000 0.0000 7
I-���� 0.0000 0.0000 0.0000 3
I-�ܷ�ǥ�� 0.0000 0.0000 0.0000 1
I-���� 0.0000 0.0000 0.0000 19
I-���̽� 0.0000 0.0000 0.0000 2
I-�޴뼺 0.0000 0.0000 0.0000 2
O 0.6756 1.0000 0.8064 152

accuracy 0.6756 225
macro avg 0.0356 0.0526 0.0424 225
weighted avg 0.4564 0.6756 0.5447 225

2024-05-27 19:47:32;[INFO];Train Loss = 73.6145791709423 Valid Loss = 49.402870178222656
2024-05-27 19:47:33;[INFO];[Now Epoch: 1]
2024-05-27 20:15:43;[INFO];[���� ���ɾ�]: sh ./scripts_ocr/model/do_train.sh
2024-05-27 20:15:43;[INFO];[Config]
2024-05-27 20:15:43;[INFO];{'epochs': 10, 'train_batch_size': 4, 'valid_batch_size': 4, 'init_model_path': 'klue/bert-base', 'max_length': 512, 'need_birnn': 0, 'aspect_drop_ratio': 0.3, 'aspect_in_feature': 768, 'stop_patience': 3, 'train_fp': './resources_ocr/parsing_data/train/', 'valid_fp': './resources_ocr/parsing_data/valid/', 'base_path': './ckpt_ocr/model/', 'label_info_file': 'meta.bin', 'out_model_path': 'pytorch_model.bin', 'cmd': 'sh ./scripts_ocr/model/do_train.sh'}
2024-05-27 20:15:43;[INFO];>>>>>>> Device Setting
2024-05-27 20:15:43;[INFO];Now using CPU
2024-05-27 20:15:43;[INFO];>>>>>>> Now setting Aspect Category Encoder
2024-05-27 20:15:43;[INFO];>>>>>>> Now setting train/valid DataLoaders
2024-05-27 20:15:43;[DEBUG];Starting new HTTPS connection (1): huggingface.co:443
2024-05-27 20:15:43;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 20:15:44;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/vocab.txt HTTP/1.1" 200 0
2024-05-27 20:15:44;[INFO];>>>>>>> Now setting Model Architecture
2024-05-27 20:15:44;[DEBUG];https://huggingface.co:443 "HEAD /klue/bert-base/resolve/main/config.json HTTP/1.1" 200 0
2024-05-27 20:15:46;[INFO];>>>>>>> Training Start!
2024-05-27 20:15:46;[INFO];[Now Epoch: 0]
2024-05-27 20:25:35;[INFO];*****eval metrics*****
2024-05-27 20:25:35;[INFO];eval_loss: 49.717087745666504
2024-05-27 20:25:35;[INFO];eval_runtime: 0:00:30.348411
2024-05-27 20:25:35;[INFO];eval_samples: 8
2024-05-27 20:25:35;[INFO];eval_samples_per_second: 0:00:03.793551
2024-05-27 20:25:35;[INFO];Aspect Accuracy: 0.55
2024-05-27 20:25:35;[INFO];Aspect f1score micro : 0.55
2024-05-27 20:25:35;[INFO];Aspect Accuracy Report:
2024-05-27 20:25:35;[INFO]; precision recall f1-score support

B-�������� 0.0000 0.0000 0.0000 11
B-���������� 0.0000 0.0000 0.0000 1
B-�������� 0.0000 0.0000 0.0000 1
B-��Ƽ��Ʈ 0.0000 0.0000 0.0000 4
B-���� 0.0000 0.0000 0.0000 2
B-�ܷ�ǥ�� 0.0000 0.0000 0.0000 2
B-���� 0.0000 0.0000 0.0000 2
B-���̽� 0.0000 0.0000 0.0000 2
B-�޴뼺 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 8
I-���������� 0.0000 0.0000 0.0000 2
I-�������� 0.0000 0.0000 0.0000 2
I-��Ƽ��Ʈ 0.0000 0.0000 0.0000 7
I-���� 0.0000 0.0000 0.0000 3
I-�ܷ�ǥ�� 0.0000 0.0000 0.0000 1
I-���� 0.0000 0.0000 0.0000 19
I-���̽� 0.0000 0.0000 0.0000 2
I-�޴뼺 0.0000 0.0000 0.0000 2
O 0.6756 1.0000 0.8064 152

accuracy 0.6756 225
macro avg 0.0356 0.0526 0.0424 225
weighted avg 0.4564 0.6756 0.5447 225

2024-05-27 20:25:36;[INFO];Train Loss = 70.5297135412693 Valid Loss = 49.717087745666504
2024-05-27 20:25:38;[INFO];[Now Epoch: 1]
Loading