Hugging Face's logo

HueyNemud
/
icdar23-entrydetector_plaintext_breaks_indents_left_ref_right_ref

Token Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
HueyNemud commited on
Commit
eb5a41d
•
1 Parent(s): dfc1d65

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -27
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: 0.0054
17
- - Ebegin: {'precision': 0.9887267904509284, 'recall': 0.9933377748167888, 'f1': 0.9910269192422732, 'number': 3002}
18
- - Eend: {'precision': 0.987396351575456, 'recall': 0.9923333333333333, 'f1': 0.9898586866167913, 'number': 3000}
19
- - Overall Precision: 0.9881
20
- - Overall Recall: 0.9928
21
- - Overall F1: 0.9904
22
- - Overall Accuracy: 0.9985
23
 
24
  ## Model description
25
 
@@ -50,26 +50,14 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
53
- | No log | 0.07 | 300 | 0.0275 | 0.9701 | 0.9913 | 0.9806 | 0.9968 |
54
- | 0.1353 | 0.14 | 600 | 0.0135 | 0.9783 | 0.9907 | 0.9845 | 0.9974 |
55
- | 0.1353 | 0.21 | 900 | 0.0106 | 0.9760 | 0.9950 | 0.9854 | 0.9976 |
56
- | 0.0152 | 0.29 | 1200 | 0.0070 | 0.9900 | 0.9898 | 0.9899 | 0.9983 |
57
- | 0.0095 | 0.36 | 1500 | 0.0065 | 0.9858 | 0.9931 | 0.9895 | 0.9983 |
58
- | 0.0095 | 0.43 | 1800 | 0.0129 | 0.9973 | 0.9682 | 0.9825 | 0.9972 |
59
- | 0.0079 | 0.5 | 2100 | 0.0058 | 0.9885 | 0.9935 | 0.9910 | 0.9985 |
60
- | 0.0079 | 0.57 | 2400 | 0.0050 | 0.9929 | 0.9886 | 0.9908 | 0.9985 |
61
- | 0.0069 | 0.64 | 2700 | 0.0049 | 0.9956 | 0.9829 | 0.9892 | 0.9982 |
62
- | 0.0058 | 0.72 | 3000 | 0.0056 | 0.9810 | 0.9968 | 0.9888 | 0.9981 |
63
- | 0.0058 | 0.79 | 3300 | 0.0043 | 0.9884 | 0.9957 | 0.9921 | 0.9987 |
64
- | 0.0057 | 0.86 | 3600 | 0.0048 | 0.9845 | 0.9965 | 0.9905 | 0.9984 |
65
- | 0.0057 | 0.93 | 3900 | 0.0043 | 0.9874 | 0.9964 | 0.9919 | 0.9986 |
66
- | 0.0046 | 1.0 | 4200 | 0.0052 | 0.9844 | 0.9974 | 0.9909 | 0.9985 |
67
- | 0.0037 | 1.07 | 4500 | 0.0036 | 0.9906 | 0.9935 | 0.9921 | 0.9987 |
68
- | 0.0037 | 1.14 | 4800 | 0.0054 | 0.9893 | 0.9952 | 0.9922 | 0.9987 |
69
- | 0.0036 | 1.22 | 5100 | 0.0040 | 0.9881 | 0.9956 | 0.9918 | 0.9986 |
70
- | 0.0036 | 1.29 | 5400 | 0.0039 | 0.9885 | 0.9961 | 0.9923 | 0.9987 |
71
- | 0.0036 | 1.36 | 5700 | 0.0037 | 0.9885 | 0.9961 | 0.9923 | 0.9987 |
72
- | 0.003 | 1.43 | 6000 | 0.0037 | 0.9884 | 0.9962 | 0.9922 | 0.9987 |
73
 
74
 
75
  ### Framework versions
 
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: 0.0084
17
+ - Ebegin: {'precision': 0.9916415914409896, 'recall': 0.9880079946702198, 'f1': 0.9898214583680961, 'number': 3002}
18
+ - Eend: {'precision': 0.9879919946631087, 'recall': 0.9873333333333333, 'f1': 0.9876625541847281, 'number': 3000}
19
+ - Overall Precision: 0.9898
20
+ - Overall Recall: 0.9877
21
+ - Overall F1: 0.9887
22
+ - Overall Accuracy: 0.9982
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
53
+ | No log | 0.07 | 300 | 0.0364 | 0.9697 | 0.9694 | 0.9695 | 0.9949 |
54
+ | 0.1737 | 0.14 | 600 | 0.0146 | 0.9849 | 0.9880 | 0.9865 | 0.9977 |
55
+ | 0.1737 | 0.21 | 900 | 0.0092 | 0.9835 | 0.9929 | 0.9881 | 0.9980 |
56
+ | 0.0158 | 0.29 | 1200 | 0.0074 | 0.9904 | 0.9912 | 0.9908 | 0.9984 |
57
+ | 0.0098 | 0.36 | 1500 | 0.0058 | 0.9866 | 0.9943 | 0.9904 | 0.9984 |
58
+ | 0.0098 | 0.43 | 1800 | 0.0075 | 0.9883 | 0.9898 | 0.9890 | 0.9982 |
59
+ | 0.0073 | 0.5 | 2100 | 0.0068 | 0.9962 | 0.9815 | 0.9888 | 0.9981 |
60
+ | 0.0073 | 0.57 | 2400 | 0.0065 | 0.9899 | 0.9900 | 0.9899 | 0.9983 |
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions