Hugging Face's logo

jordyvl
/
EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted

Text Classification
Transformers
PyTorch
layoutlmv3
Generated from Trainer
Inference Endpoints
Model card Files Community
jordyvl commited on
Commit
47a454e
•
1 Parent(s): 369d148

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +125 -0
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-07-05_weighted
16
+
17
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.0783
20
+ - Accuracy: 0.71
21
+ - Exit 0 Accuracy: 0.115
22
+ - Exit 1 Accuracy: 0.1575
23
+ - Exit 2 Accuracy: 0.185
24
+ - Exit 3 Accuracy: 0.0875
25
+ - Exit 4 Accuracy: 0.0625
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 2e-05
45
+ - train_batch_size: 12
46
+ - eval_batch_size: 4
47
+ - seed: 42
48
+ - gradient_accumulation_steps: 24
49
+ - total_train_batch_size: 288
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 60
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
58
+ | No log | 0.72 | 2 | 2.7602 | 0.1125 | 0.0925 | 0.0675 | 0.0875 | 0.0625 | 0.0625 |
59
+ | No log | 1.72 | 4 | 2.7309 | 0.115 | 0.1175 | 0.0675 | 0.1075 | 0.0625 | 0.0625 |
60
+ | No log | 2.72 | 6 | 2.6967 | 0.1325 | 0.095 | 0.06 | 0.1175 | 0.0625 | 0.0625 |
61
+ | No log | 3.72 | 8 | 2.6631 | 0.17 | 0.085 | 0.0575 | 0.1275 | 0.0625 | 0.0625 |
62
+ | No log | 4.72 | 10 | 2.6242 | 0.205 | 0.085 | 0.0575 | 0.1225 | 0.0625 | 0.0625 |
63
+ | No log | 5.72 | 12 | 2.5736 | 0.2175 | 0.0875 | 0.0825 | 0.12 | 0.0625 | 0.0625 |
64
+ | No log | 6.72 | 14 | 2.5410 | 0.215 | 0.09 | 0.08 | 0.12 | 0.0625 | 0.0625 |
65
+ | No log | 7.72 | 16 | 2.5229 | 0.2325 | 0.1 | 0.0925 | 0.13 | 0.0625 | 0.0625 |
66
+ | No log | 8.72 | 18 | 2.4841 | 0.2525 | 0.1 | 0.1 | 0.1325 | 0.0625 | 0.0625 |
67
+ | No log | 9.72 | 20 | 2.4382 | 0.29 | 0.1 | 0.1025 | 0.1325 | 0.0625 | 0.0625 |
68
+ | No log | 10.72 | 22 | 2.3823 | 0.3 | 0.1 | 0.1275 | 0.1325 | 0.0625 | 0.0625 |
69
+ | No log | 11.72 | 24 | 2.3389 | 0.3275 | 0.1 | 0.1175 | 0.1225 | 0.0625 | 0.0625 |
70
+ | No log | 12.72 | 26 | 2.3002 | 0.35 | 0.0975 | 0.12 | 0.1225 | 0.0625 | 0.0625 |
71
+ | No log | 13.72 | 28 | 2.2421 | 0.36 | 0.0975 | 0.125 | 0.1275 | 0.0625 | 0.0625 |
72
+ | No log | 14.72 | 30 | 2.2026 | 0.3575 | 0.1025 | 0.13 | 0.125 | 0.0625 | 0.0625 |
73
+ | No log | 15.72 | 32 | 2.1712 | 0.375 | 0.105 | 0.1375 | 0.125 | 0.0625 | 0.0625 |
74
+ | No log | 16.72 | 34 | 2.0999 | 0.4075 | 0.1 | 0.145 | 0.125 | 0.0625 | 0.0625 |
75
+ | No log | 17.72 | 36 | 2.0414 | 0.4225 | 0.1025 | 0.145 | 0.1275 | 0.0625 | 0.0625 |
76
+ | No log | 18.72 | 38 | 1.9981 | 0.4375 | 0.0975 | 0.1425 | 0.13 | 0.0625 | 0.0625 |
77
+ | No log | 19.72 | 40 | 1.9369 | 0.4575 | 0.1025 | 0.14 | 0.1425 | 0.0625 | 0.0625 |
78
+ | No log | 20.72 | 42 | 1.8903 | 0.4975 | 0.1025 | 0.14 | 0.145 | 0.0625 | 0.0625 |
79
+ | No log | 21.72 | 44 | 1.8242 | 0.525 | 0.1025 | 0.1425 | 0.15 | 0.0625 | 0.0625 |
80
+ | No log | 22.72 | 46 | 1.7520 | 0.5325 | 0.11 | 0.1475 | 0.1475 | 0.0625 | 0.0625 |
81
+ | No log | 23.72 | 48 | 1.7203 | 0.5525 | 0.1125 | 0.1475 | 0.1525 | 0.0625 | 0.0625 |
82
+ | No log | 24.72 | 50 | 1.6753 | 0.565 | 0.1125 | 0.1475 | 0.155 | 0.0625 | 0.0625 |
83
+ | No log | 25.72 | 52 | 1.6245 | 0.575 | 0.1125 | 0.1475 | 0.155 | 0.0625 | 0.0625 |
84
+ | No log | 26.72 | 54 | 1.5832 | 0.61 | 0.11 | 0.15 | 0.1525 | 0.0625 | 0.0625 |
85
+ | No log | 27.72 | 56 | 1.5404 | 0.61 | 0.11 | 0.1475 | 0.155 | 0.0625 | 0.0625 |
86
+ | No log | 28.72 | 58 | 1.4958 | 0.6125 | 0.11 | 0.1475 | 0.1575 | 0.0625 | 0.0625 |
87
+ | No log | 29.72 | 60 | 1.4613 | 0.6325 | 0.11 | 0.1475 | 0.1575 | 0.0625 | 0.0625 |
88
+ | No log | 30.72 | 62 | 1.4479 | 0.63 | 0.11 | 0.1525 | 0.16 | 0.0625 | 0.0625 |
89
+ | No log | 31.72 | 64 | 1.4101 | 0.64 | 0.1125 | 0.1525 | 0.165 | 0.0625 | 0.0625 |
90
+ | No log | 32.72 | 66 | 1.3699 | 0.655 | 0.1125 | 0.1525 | 0.1675 | 0.0625 | 0.0625 |
91
+ | No log | 33.72 | 68 | 1.3427 | 0.6725 | 0.115 | 0.1525 | 0.165 | 0.0625 | 0.0625 |
92
+ | No log | 34.72 | 70 | 1.3161 | 0.6825 | 0.115 | 0.1525 | 0.1625 | 0.0625 | 0.0625 |
93
+ | No log | 35.72 | 72 | 1.2896 | 0.7025 | 0.115 | 0.1525 | 0.1675 | 0.0625 | 0.0625 |
94
+ | No log | 36.72 | 74 | 1.2720 | 0.705 | 0.11 | 0.1525 | 0.185 | 0.0625 | 0.0625 |
95
+ | No log | 37.72 | 76 | 1.2471 | 0.71 | 0.11 | 0.1525 | 0.1775 | 0.0625 | 0.0625 |
96
+ | No log | 38.72 | 78 | 1.2307 | 0.71 | 0.11 | 0.155 | 0.1775 | 0.0625 | 0.0625 |
97
+ | No log | 39.72 | 80 | 1.2174 | 0.7175 | 0.1125 | 0.155 | 0.1825 | 0.0625 | 0.0625 |
98
+ | No log | 40.72 | 82 | 1.1991 | 0.705 | 0.1125 | 0.1525 | 0.1775 | 0.0625 | 0.0625 |
99
+ | No log | 41.72 | 84 | 1.1867 | 0.71 | 0.1175 | 0.1525 | 0.18 | 0.065 | 0.0625 |
100
+ | No log | 42.72 | 86 | 1.1764 | 0.7025 | 0.115 | 0.1525 | 0.18 | 0.0675 | 0.0625 |
101
+ | No log | 43.72 | 88 | 1.1601 | 0.715 | 0.115 | 0.1525 | 0.1825 | 0.0725 | 0.0625 |
102
+ | No log | 44.72 | 90 | 1.1410 | 0.7175 | 0.115 | 0.1525 | 0.18 | 0.075 | 0.0625 |
103
+ | No log | 45.72 | 92 | 1.1408 | 0.71 | 0.115 | 0.155 | 0.1825 | 0.075 | 0.0625 |
104
+ | No log | 46.72 | 94 | 1.1443 | 0.7075 | 0.115 | 0.155 | 0.1825 | 0.0775 | 0.0625 |
105
+ | No log | 47.72 | 96 | 1.1364 | 0.705 | 0.115 | 0.155 | 0.1775 | 0.0825 | 0.0625 |
106
+ | No log | 48.72 | 98 | 1.1251 | 0.71 | 0.115 | 0.155 | 0.175 | 0.085 | 0.0625 |
107
+ | No log | 49.72 | 100 | 1.1113 | 0.7175 | 0.115 | 0.155 | 0.1775 | 0.085 | 0.0625 |
108
+ | No log | 50.72 | 102 | 1.1040 | 0.7175 | 0.115 | 0.155 | 0.18 | 0.0875 | 0.0625 |
109
+ | No log | 51.72 | 104 | 1.0972 | 0.715 | 0.115 | 0.155 | 0.18 | 0.0875 | 0.0625 |
110
+ | No log | 52.72 | 106 | 1.0938 | 0.7175 | 0.115 | 0.1575 | 0.1825 | 0.0875 | 0.0625 |
111
+ | No log | 53.72 | 108 | 1.0931 | 0.71 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 |
112
+ | No log | 54.72 | 110 | 1.0887 | 0.7075 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 |
113
+ | No log | 55.72 | 112 | 1.0865 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 |
114
+ | No log | 56.72 | 114 | 1.0828 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 |
115
+ | No log | 57.72 | 116 | 1.0801 | 0.7075 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 |
116
+ | No log | 58.72 | 118 | 1.0786 | 0.7125 | 0.115 | 0.1575 | 0.1875 | 0.0875 | 0.0625 |
117
+ | No log | 59.72 | 120 | 1.0783 | 0.71 | 0.115 | 0.1575 | 0.185 | 0.0875 | 0.0625 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.26.1
123
+ - Pytorch 1.13.1.post200
124
+ - Datasets 2.9.0
125
+ - Tokenizers 0.13.2