Hugging Face's logo

bao121
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
TensorBoard
Safetensors
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bao121 commited on
Commit
102737c
·
verified ·
1 Parent(s): 60da493

End of training

Browse files
Files changed (1) hide show
  1. README.md +147 -0
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-sa-4.0
4
+ base_model: microsoft/layoutlmv2-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: layoutlmv2-base-uncased_finetuned_docvqa
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
+ # layoutlmv2-base-uncased_finetuned_docvqa
16
+
17
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 4.9512
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 20
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-------:|:----:|:---------------:|
50
+ | 5.2951 | 0.2212 | 50 | 4.7074 |
51
+ | 4.5271 | 0.4425 | 100 | 4.1032 |
52
+ | 4.1303 | 0.6637 | 150 | 3.9369 |
53
+ | 3.8633 | 0.8850 | 200 | 3.5651 |
54
+ | 3.4747 | 1.1062 | 250 | 3.6489 |
55
+ | 3.4294 | 1.3274 | 300 | 3.1484 |
56
+ | 3.1319 | 1.5487 | 350 | 2.9161 |
57
+ | 2.8258 | 1.7699 | 400 | 2.8137 |
58
+ | 2.6171 | 1.9912 | 450 | 2.9083 |
59
+ | 2.4222 | 2.2124 | 500 | 3.0206 |
60
+ | 2.1271 | 2.4336 | 550 | 2.6056 |
61
+ | 1.9083 | 2.6549 | 600 | 2.3721 |
62
+ | 1.9685 | 2.8761 | 650 | 2.3992 |
63
+ | 1.6307 | 3.0973 | 700 | 2.7301 |
64
+ | 1.4481 | 3.3186 | 750 | 2.3406 |
65
+ | 1.4984 | 3.5398 | 800 | 2.6880 |
66
+ | 1.7125 | 3.7611 | 850 | 2.4609 |
67
+ | 1.3863 | 3.9823 | 900 | 2.3533 |
68
+ | 1.2462 | 4.2035 | 950 | 2.5440 |
69
+ | 1.0761 | 4.4248 | 1000 | 2.7272 |
70
+ | 1.1144 | 4.6460 | 1050 | 1.9797 |
71
+ | 0.9787 | 4.8673 | 1100 | 2.4466 |
72
+ | 0.8171 | 5.0885 | 1150 | 2.9085 |
73
+ | 0.8736 | 5.3097 | 1200 | 2.9959 |
74
+ | 0.9349 | 5.5310 | 1250 | 2.3175 |
75
+ | 0.7439 | 5.7522 | 1300 | 3.0023 |
76
+ | 0.7007 | 5.9735 | 1350 | 3.1554 |
77
+ | 0.4858 | 6.1947 | 1400 | 3.3196 |
78
+ | 0.7693 | 6.4159 | 1450 | 3.3589 |
79
+ | 0.4525 | 6.6372 | 1500 | 3.1226 |
80
+ | 0.442 | 6.8584 | 1550 | 3.5817 |
81
+ | 0.5321 | 7.0796 | 1600 | 3.4303 |
82
+ | 0.4044 | 7.3009 | 1650 | 3.5700 |
83
+ | 0.3062 | 7.5221 | 1700 | 4.0335 |
84
+ | 0.5116 | 7.7434 | 1750 | 3.6335 |
85
+ | 0.3481 | 7.9646 | 1800 | 3.5987 |
86
+ | 0.2781 | 8.1858 | 1850 | 4.0488 |
87
+ | 0.3054 | 8.4071 | 1900 | 3.4694 |
88
+ | 0.3572 | 8.6283 | 1950 | 3.7605 |
89
+ | 0.3524 | 8.8496 | 2000 | 3.9977 |
90
+ | 0.3551 | 9.0708 | 2050 | 3.7106 |
91
+ | 0.1455 | 9.2920 | 2100 | 3.8854 |
92
+ | 0.3655 | 9.5133 | 2150 | 3.6476 |
93
+ | 0.348 | 9.7345 | 2200 | 3.5709 |
94
+ | 0.299 | 9.9558 | 2250 | 3.6914 |
95
+ | 0.1781 | 10.1770 | 2300 | 3.7616 |
96
+ | 0.1812 | 10.3982 | 2350 | 3.7328 |
97
+ | 0.3197 | 10.6195 | 2400 | 4.3628 |
98
+ | 0.2139 | 10.8407 | 2450 | 4.3765 |
99
+ | 0.0266 | 11.0619 | 2500 | 4.6882 |
100
+ | 0.0659 | 11.2832 | 2550 | 4.5060 |
101
+ | 0.2312 | 11.5044 | 2600 | 4.1473 |
102
+ | 0.1366 | 11.7257 | 2650 | 4.2983 |
103
+ | 0.2264 | 11.9469 | 2700 | 4.2400 |
104
+ | 0.165 | 12.1681 | 2750 | 4.0799 |
105
+ | 0.0443 | 12.3894 | 2800 | 4.2081 |
106
+ | 0.178 | 12.6106 | 2850 | 4.0656 |
107
+ | 0.2517 | 12.8319 | 2900 | 4.2621 |
108
+ | 0.1208 | 13.0531 | 2950 | 4.6150 |
109
+ | 0.0767 | 13.2743 | 3000 | 4.6056 |
110
+ | 0.0789 | 13.4956 | 3050 | 4.2637 |
111
+ | 0.0492 | 13.7168 | 3100 | 4.3896 |
112
+ | 0.1782 | 13.9381 | 3150 | 4.3427 |
113
+ | 0.0968 | 14.1593 | 3200 | 4.5666 |
114
+ | 0.0287 | 14.3805 | 3250 | 4.6159 |
115
+ | 0.0516 | 14.6018 | 3300 | 4.4566 |
116
+ | 0.1008 | 14.8230 | 3350 | 4.5481 |
117
+ | 0.052 | 15.0442 | 3400 | 4.6010 |
118
+ | 0.0334 | 15.2655 | 3450 | 4.6442 |
119
+ | 0.027 | 15.4867 | 3500 | 4.7174 |
120
+ | 0.0791 | 15.7080 | 3550 | 4.5374 |
121
+ | 0.147 | 15.9292 | 3600 | 4.6980 |
122
+ | 0.1186 | 16.1504 | 3650 | 4.5936 |
123
+ | 0.0373 | 16.3717 | 3700 | 4.6215 |
124
+ | 0.0445 | 16.5929 | 3750 | 4.4737 |
125
+ | 0.0325 | 16.8142 | 3800 | 4.6176 |
126
+ | 0.0842 | 17.0354 | 3850 | 4.7082 |
127
+ | 0.0097 | 17.2566 | 3900 | 4.7821 |
128
+ | 0.0707 | 17.4779 | 3950 | 4.7606 |
129
+ | 0.0583 | 17.6991 | 4000 | 4.8275 |
130
+ | 0.0222 | 17.9204 | 4050 | 4.8638 |
131
+ | 0.0413 | 18.1416 | 4100 | 4.8912 |
132
+ | 0.0097 | 18.3628 | 4150 | 4.9439 |
133
+ | 0.0075 | 18.5841 | 4200 | 4.9960 |
134
+ | 0.0735 | 18.8053 | 4250 | 4.9482 |
135
+ | 0.0821 | 19.0265 | 4300 | 5.0201 |
136
+ | 0.0254 | 19.2478 | 4350 | 4.9772 |
137
+ | 0.1105 | 19.4690 | 4400 | 4.9629 |
138
+ | 0.0649 | 19.6903 | 4450 | 4.9474 |
139
+ | 0.025 | 19.9115 | 4500 | 4.9512 |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - Transformers 4.45.2
145
+ - Pytorch 2.5.0
146
+ - Datasets 3.0.1
147
+ - Tokenizers 0.20.1