Hugging Face's logo

HueyNemud
/
icdar23-entrydetector_plaintext_breaks_indents_left_ref

Token Classification
Transformers
PyTorch
camembert
Generated from Trainer
Inference Endpoints
Model card Files Community
HueyNemud commited on
Commit
051aa31
•
1 Parent(s): bc5f4d5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -16
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: 0.0090
17
- - Ebegin: {'precision': 0.9861248761149654, 'recall': 0.9943371085942705, 'f1': 0.9902139658318129, 'number': 3002}
18
- - Eend: {'precision': 0.9858038956751403, 'recall': 0.9953333333333333, 'f1': 0.9905456958036158, 'number': 3000}
19
- - Overall Precision: 0.9860
20
- - Overall Recall: 0.9948
21
- - Overall F1: 0.9904
22
- - Overall Accuracy: 0.9985
23
 
24
  ## Model description
25
 
@@ -44,24 +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 | 0.0375 | 0.9526 | 0.9799 | 0.9661 | 0.9949 |
54
- | 0.1677 | 0.14 | 600 | 0.0134 | 0.9792 | 0.9936 | 0.9864 | 0.9976 |
55
- | 0.1677 | 0.21 | 900 | 0.0103 | 0.9866 | 0.9933 | 0.9899 | 0.9982 |
56
- | 0.0164 | 0.29 | 1200 | 0.0085 | 0.9903 | 0.9887 | 0.9895 | 0.9981 |
57
- | 0.0095 | 0.36 | 1500 | 0.0087 | 0.9877 | 0.9906 | 0.9892 | 0.9981 |
58
- | 0.0095 | 0.43 | 1800 | 0.0063 | 0.9953 | 0.9826 | 0.9889 | 0.9980 |
59
- | 0.0085 | 0.5 | 2100 | 0.0071 | 0.9887 | 0.9893 | 0.9890 | 0.9980 |
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.26.0
65
  - Pytorch 1.13.1+cu116
66
  - Datasets 2.9.0
67
  - 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: 0.0079
17
+ - Ebegin: {'precision': 0.9973414356247626, 'recall': 0.9875893192929672, 'f1': 0.9924414210128495, 'number': 2659}
18
+ - Eend: {'precision': 0.9980966882375333, 'recall': 0.9798206278026906, 'f1': 0.9888742221384123, 'number': 2676}
19
+ - Overall Precision: 0.9977
20
+ - Overall Recall: 0.9837
21
+ - Overall F1: 0.9907
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 | 0.0341 | 0.9873 | 0.9698 | 0.9785 | 0.9966 |
54
+ | 0.173 | 0.14 | 600 | 0.0140 | 0.9895 | 0.9899 | 0.9897 | 0.9982 |
55
+ | 0.173 | 0.21 | 900 | 0.0135 | 0.9796 | 0.9884 | 0.9840 | 0.9973 |
56
+ | 0.0216 | 0.29 | 1200 | 0.0087 | 0.9938 | 0.9901 | 0.9920 | 0.9986 |
57
+ | 0.0138 | 0.36 | 1500 | 0.0061 | 0.9884 | 0.9938 | 0.9911 | 0.9984 |
58
+ | 0.0138 | 0.43 | 1800 | 0.0060 | 0.9938 | 0.9919 | 0.9929 | 0.9987 |
59
+ | 0.0083 | 0.5 | 2100 | 0.0058 | 0.9963 | 0.9909 | 0.9935 | 0.9989 |
60
+ | 0.0083 | 0.57 | 2400 | 0.0064 | 0.9972 | 0.9913 | 0.9942 | 0.9990 |
61
+ | 0.0092 | 0.64 | 2700 | 0.0083 | 0.9881 | 0.9947 | 0.9914 | 0.9985 |
62
+ | 0.0087 | 0.72 | 3000 | 0.0057 | 0.9924 | 0.9934 | 0.9929 | 0.9987 |
63
+ | 0.0087 | 0.79 | 3300 | 0.0044 | 0.9925 | 0.9927 | 0.9926 | 0.9987 |
64
+ | 0.0066 | 0.86 | 3600 | 0.0049 | 0.9948 | 0.9917 | 0.9932 | 0.9988 |
65
+ | 0.0066 | 0.93 | 3900 | 0.0082 | 0.9886 | 0.9916 | 0.9901 | 0.9982 |
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