Hugging Face's logo

HueyNemud
/
icdar23-entrydetector_plaintext_breaks_indents_left_diff_right_ref

Token Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
HueyNemud commited on
Commit
98fce33
•
1 Parent(s): 5a224c0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -29
README.md CHANGED
@@ -13,13 +13,13 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [HueyNemud/das22-10-camembert_pretrained](https://huggingface.co/HueyNemud/das22-10-camembert_pretrained) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.0046
17
- - Ebegin: {'precision': 0.9946541931172737, 'recall': 0.991672218520986, 'f1': 0.9931609674728941, 'number': 3002}
18
- - Eend: {'precision': 0.9858412907474481, 'recall': 0.998, 'f1': 0.9918833857876428, 'number': 3000}
19
- - Overall Precision: 0.9902
20
- - Overall Recall: 0.9948
21
- - Overall F1: 0.9925
22
- - Overall Accuracy: 0.9988
23
 
24
  ## Model description
25
 
@@ -44,37 +44,30 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - training_steps: 6000
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
53
- | No log | 0.07 | 300 | 0.0323 | 0.9553 | 0.9933 | 0.9740 | 0.9955 |
54
- | 0.1598 | 0.14 | 600 | 0.0119 | 0.9817 | 0.9931 | 0.9874 | 0.9979 |
55
- | 0.1598 | 0.21 | 900 | 0.0107 | 0.9817 | 0.9944 | 0.9880 | 0.9980 |
56
- | 0.016 | 0.29 | 1200 | 0.0066 | 0.9889 | 0.9907 | 0.9898 | 0.9984 |
57
- | 0.0098 | 0.36 | 1500 | 0.0058 | 0.9845 | 0.9945 | 0.9894 | 0.9982 |
58
- | 0.0098 | 0.43 | 1800 | 0.0071 | 0.9927 | 0.9862 | 0.9895 | 0.9982 |
59
- | 0.0079 | 0.5 | 2100 | 0.0054 | 0.9884 | 0.9940 | 0.9912 | 0.9985 |
60
- | 0.0079 | 0.57 | 2400 | 0.0049 | 0.9930 | 0.9885 | 0.9908 | 0.9985 |
61
- | 0.0061 | 0.64 | 2700 | 0.0059 | 0.9979 | 0.9781 | 0.9879 | 0.9980 |
62
- | 0.0066 | 0.72 | 3000 | 0.0046 | 0.9882 | 0.9956 | 0.9919 | 0.9986 |
63
- | 0.0066 | 0.79 | 3300 | 0.0043 | 0.9861 | 0.9971 | 0.9916 | 0.9986 |
64
- | 0.0066 | 0.86 | 3600 | 0.0038 | 0.9876 | 0.9968 | 0.9922 | 0.9987 |
65
- | 0.0066 | 0.93 | 3900 | 0.0046 | 0.9888 | 0.9961 | 0.9924 | 0.9987 |
66
- | 0.0044 | 1.0 | 4200 | 0.0042 | 0.9880 | 0.9965 | 0.9922 | 0.9987 |
67
- | 0.0035 | 1.07 | 4500 | 0.0038 | 0.9870 | 0.9975 | 0.9922 | 0.9987 |
68
- | 0.0035 | 1.14 | 4800 | 0.0038 | 0.9902 | 0.9951 | 0.9927 | 0.9988 |
69
- | 0.0035 | 1.22 | 5100 | 0.0037 | 0.9897 | 0.9949 | 0.9923 | 0.9987 |
70
- | 0.0035 | 1.29 | 5400 | 0.0038 | 0.9946 | 0.9901 | 0.9924 | 0.9987 |
71
- | 0.0028 | 1.36 | 5700 | 0.0038 | 0.9888 | 0.9963 | 0.9926 | 0.9988 |
72
- | 0.0024 | 1.43 | 6000 | 0.0038 | 0.9885 | 0.9966 | 0.9926 | 0.9988 |
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.26.0
78
  - Pytorch 1.13.1+cu116
79
  - Datasets 2.9.0
80
  - Tokenizers 0.13.2
 
13
 
14
  This model is a fine-tuned version of [HueyNemud/das22-10-camembert_pretrained](https://huggingface.co/HueyNemud/das22-10-camembert_pretrained) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.0052
17
+ - Ebegin: {'precision': 0.9891263592050994, 'recall': 0.9921022940955246, 'f1': 0.9906120916259857, 'number': 2659}
18
+ - Eend: {'precision': 0.9947029890276201, 'recall': 0.9824364723467862, 'f1': 0.9885316788870088, 'number': 2676}
19
+ - Overall Precision: 0.9919
20
+ - Overall Recall: 0.9873
21
+ - Overall F1: 0.9896
22
+ - Overall Accuracy: 0.9984
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - training_steps: 7500
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
53
+ | No log | 0.07 | 300 | 0.0329 | 0.9706 | 0.9804 | 0.9755 | 0.9968 |
54
+ | 0.1902 | 0.14 | 600 | 0.0141 | 0.9815 | 0.9919 | 0.9867 | 0.9978 |
55
+ | 0.1902 | 0.21 | 900 | 0.0130 | 0.9853 | 0.9866 | 0.9860 | 0.9976 |
56
+ | 0.0162 | 0.29 | 1200 | 0.0110 | 0.9835 | 0.9932 | 0.9883 | 0.9981 |
57
+ | 0.0102 | 0.36 | 1500 | 0.0086 | 0.9856 | 0.9943 | 0.9899 | 0.9983 |
58
+ | 0.0102 | 0.43 | 1800 | 0.0052 | 0.9921 | 0.9909 | 0.9915 | 0.9987 |
59
+ | 0.0071 | 0.5 | 2100 | 0.0061 | 0.9915 | 0.9913 | 0.9914 | 0.9986 |
60
+ | 0.0071 | 0.57 | 2400 | 0.0053 | 0.9938 | 0.9915 | 0.9927 | 0.9988 |
61
+ | 0.0083 | 0.64 | 2700 | 0.0054 | 0.9905 | 0.9902 | 0.9904 | 0.9984 |
62
+ | 0.0058 | 0.72 | 3000 | 0.0060 | 0.9843 | 0.9953 | 0.9898 | 0.9983 |
63
+ | 0.0058 | 0.79 | 3300 | 0.0050 | 0.9919 | 0.9933 | 0.9926 | 0.9988 |
64
+ | 0.0067 | 0.86 | 3600 | 0.0062 | 0.9905 | 0.9935 | 0.9920 | 0.9987 |
65
+ | 0.0067 | 0.93 | 3900 | 0.0049 | 0.9883 | 0.9956 | 0.9919 | 0.9986 |
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
+ - Transformers 4.26.1
71
  - Pytorch 1.13.1+cu116
72
  - Datasets 2.9.0
73
  - Tokenizers 0.13.2