HueyNemud commited on
Commit
318138f
1 Parent(s): a3b389f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: icdar23-entrydetector_plaintext_breaks_indents_left_diff_right_ref
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # icdar23-entrydetector_plaintext_breaks_indents_left_diff_right_ref
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': 0.9894004637297118, 'recall': 0.9950033311125916, 'f1': 0.9921939877096828, 'number': 3002}
18
+ - Eend: {'precision': 0.9909879839786382, 'recall': 0.9896666666666667, 'f1': 0.9903268845897265, 'number': 3000}
19
+ - Overall Precision: 0.9902
20
+ - Overall Recall: 0.9923
21
+ - Overall F1: 0.9913
22
+ - Overall Accuracy: 0.9986
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 2
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 | 0.0273 | 0.9720 | 0.9930 | 0.9824 | 0.9970 |
54
+ | 0.1622 | 0.14 | 600 | 0.0127 | 0.9798 | 0.9947 | 0.9871 | 0.9978 |
55
+ | 0.1622 | 0.21 | 900 | 0.0104 | 0.9833 | 0.9911 | 0.9872 | 0.9979 |
56
+ | 0.0167 | 0.29 | 1200 | 0.0066 | 0.9829 | 0.9953 | 0.9890 | 0.9982 |
57
+ | 0.0098 | 0.36 | 1500 | 0.0071 | 0.9776 | 0.9962 | 0.9868 | 0.9978 |
58
+ | 0.0098 | 0.43 | 1800 | 0.0048 | 0.9895 | 0.9944 | 0.9919 | 0.9986 |
59
+ | 0.0065 | 0.5 | 2100 | 0.0069 | 0.9892 | 0.9933 | 0.9912 | 0.9985 |
60
+ | 0.0065 | 0.57 | 2400 | 0.0050 | 0.9873 | 0.9942 | 0.9907 | 0.9985 |
61
+ | 0.0066 | 0.64 | 2700 | 0.0043 | 0.9982 | 0.9846 | 0.9914 | 0.9986 |
62
+ | 0.0061 | 0.72 | 3000 | 0.0042 | 0.9906 | 0.9907 | 0.9907 | 0.9985 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.26.0
68
+ - Pytorch 1.13.1+cu116
69
+ - Datasets 2.9.0
70
+ - Tokenizers 0.13.2