Hugging Face's logo

NitishKarra
/
layoutlmv3-finetuned-wildreceipt

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
NitishKarra commited on
Commit
c8e8b60
·
1 Parent(s): 2804ece

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +128 -0
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - wildreceipt
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: layoutlmv3-finetuned-wildreceipt
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: wildreceipt
20
+ type: wildreceipt
21
+ config: WildReceipt
22
+ split: train
23
+ args: WildReceipt
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.8693453601202679
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.8753268198706481
31
+ - name: F1
32
+ type: f1
33
+ value: 0.872325836533187
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9240429965997587
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # layoutlmv3-finetuned-wildreceipt
43
+
44
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the wildreceipt dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.3154
47
+ - Precision: 0.8693
48
+ - Recall: 0.8753
49
+ - F1: 0.8723
50
+ - Accuracy: 0.9240
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 1e-05
70
+ - train_batch_size: 4
71
+ - eval_batch_size: 4
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - training_steps: 4000
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 0.32 | 100 | 1.3618 | 0.6375 | 0.3049 | 0.4125 | 0.6708 |
82
+ | No log | 0.63 | 200 | 0.9129 | 0.6662 | 0.4897 | 0.5645 | 0.7631 |
83
+ | No log | 0.95 | 300 | 0.6800 | 0.7273 | 0.6375 | 0.6795 | 0.8274 |
84
+ | No log | 1.26 | 400 | 0.5733 | 0.7579 | 0.6926 | 0.7238 | 0.8501 |
85
+ | 1.0638 | 1.58 | 500 | 0.5015 | 0.7854 | 0.7383 | 0.7611 | 0.8667 |
86
+ | 1.0638 | 1.89 | 600 | 0.4501 | 0.7916 | 0.7680 | 0.7796 | 0.8770 |
87
+ | 1.0638 | 2.21 | 700 | 0.4145 | 0.8177 | 0.8053 | 0.8114 | 0.8917 |
88
+ | 1.0638 | 2.52 | 800 | 0.3835 | 0.8214 | 0.8210 | 0.8212 | 0.8961 |
89
+ | 1.0638 | 2.84 | 900 | 0.3666 | 0.8251 | 0.8338 | 0.8294 | 0.9009 |
90
+ | 0.423 | 3.15 | 1000 | 0.3524 | 0.8485 | 0.8217 | 0.8349 | 0.9026 |
91
+ | 0.423 | 3.47 | 1100 | 0.3451 | 0.8430 | 0.8327 | 0.8378 | 0.9060 |
92
+ | 0.423 | 3.79 | 1200 | 0.3348 | 0.8347 | 0.8504 | 0.8425 | 0.9092 |
93
+ | 0.423 | 4.1 | 1300 | 0.3331 | 0.8368 | 0.8448 | 0.8408 | 0.9079 |
94
+ | 0.423 | 4.42 | 1400 | 0.3163 | 0.8503 | 0.8519 | 0.8511 | 0.9138 |
95
+ | 0.2822 | 4.73 | 1500 | 0.3168 | 0.8531 | 0.8504 | 0.8518 | 0.9133 |
96
+ | 0.2822 | 5.05 | 1600 | 0.3013 | 0.8629 | 0.8577 | 0.8603 | 0.9183 |
97
+ | 0.2822 | 5.36 | 1700 | 0.3146 | 0.8619 | 0.8528 | 0.8573 | 0.9160 |
98
+ | 0.2822 | 5.68 | 1800 | 0.3121 | 0.8474 | 0.8638 | 0.8555 | 0.9159 |
99
+ | 0.2822 | 5.99 | 1900 | 0.3054 | 0.8537 | 0.8667 | 0.8601 | 0.9166 |
100
+ | 0.2176 | 6.31 | 2000 | 0.3127 | 0.8556 | 0.8592 | 0.8574 | 0.9167 |
101
+ | 0.2176 | 6.62 | 2100 | 0.3072 | 0.8568 | 0.8667 | 0.8617 | 0.9194 |
102
+ | 0.2176 | 6.94 | 2200 | 0.2989 | 0.8617 | 0.8660 | 0.8638 | 0.9209 |
103
+ | 0.2176 | 7.26 | 2300 | 0.2997 | 0.8616 | 0.8682 | 0.8649 | 0.9199 |
104
+ | 0.2176 | 7.57 | 2400 | 0.3100 | 0.8538 | 0.8689 | 0.8613 | 0.9191 |
105
+ | 0.1777 | 7.89 | 2500 | 0.3022 | 0.8649 | 0.8695 | 0.8672 | 0.9228 |
106
+ | 0.1777 | 8.2 | 2600 | 0.2990 | 0.8631 | 0.8740 | 0.8685 | 0.9224 |
107
+ | 0.1777 | 8.52 | 2700 | 0.3072 | 0.8669 | 0.8697 | 0.8683 | 0.9228 |
108
+ | 0.1777 | 8.83 | 2800 | 0.3038 | 0.8689 | 0.8720 | 0.8705 | 0.9238 |
109
+ | 0.1777 | 9.15 | 2900 | 0.3138 | 0.8726 | 0.8673 | 0.8700 | 0.9216 |
110
+ | 0.1434 | 9.46 | 3000 | 0.3150 | 0.8610 | 0.8740 | 0.8674 | 0.9221 |
111
+ | 0.1434 | 9.78 | 3100 | 0.3055 | 0.8674 | 0.8742 | 0.8708 | 0.9239 |
112
+ | 0.1434 | 10.09 | 3200 | 0.3182 | 0.8618 | 0.8724 | 0.8671 | 0.9215 |
113
+ | 0.1434 | 10.41 | 3300 | 0.3175 | 0.8633 | 0.8727 | 0.8680 | 0.9223 |
114
+ | 0.1434 | 10.73 | 3400 | 0.3146 | 0.8685 | 0.8717 | 0.8701 | 0.9234 |
115
+ | 0.1282 | 11.04 | 3500 | 0.3136 | 0.8671 | 0.8757 | 0.8714 | 0.9233 |
116
+ | 0.1282 | 11.36 | 3600 | 0.3186 | 0.8679 | 0.8734 | 0.8706 | 0.9225 |
117
+ | 0.1282 | 11.67 | 3700 | 0.3147 | 0.8701 | 0.8745 | 0.8723 | 0.9238 |
118
+ | 0.1282 | 11.99 | 3800 | 0.3159 | 0.8705 | 0.8759 | 0.8732 | 0.9244 |
119
+ | 0.1282 | 12.3 | 3900 | 0.3147 | 0.8699 | 0.8748 | 0.8723 | 0.9246 |
120
+ | 0.1121 | 12.62 | 4000 | 0.3154 | 0.8693 | 0.8753 | 0.8723 | 0.9240 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - Transformers 4.22.0.dev0
126
+ - Pytorch 1.12.0+cu113
127
+ - Datasets 2.4.0
128
+ - Tokenizers 0.12.1