Hugging Face's logo

cfa213
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
TensorBoard
Safetensors
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cfa213 commited on
Commit
ee95f7b
•
1 Parent(s): 350b7e3

End of training

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: microsoft/layoutlmv2-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: layoutlmv2-base-uncased_finetuned_docvqa
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # layoutlmv2-base-uncased_finetuned_docvqa
15
+
16
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.6446
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 10
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:------:|:----:|:---------------:|
49
+ | 5.1899 | 0.2212 | 50 | 4.5198 |
50
+ | 4.3841 | 0.4425 | 100 | 3.9910 |
51
+ | 4.0167 | 0.6637 | 150 | 3.9030 |
52
+ | 3.7906 | 0.8850 | 200 | 3.4974 |
53
+ | 3.426 | 1.1062 | 250 | 3.7834 |
54
+ | 3.0774 | 1.3274 | 300 | 3.2013 |
55
+ | 2.9541 | 1.5487 | 350 | 3.0711 |
56
+ | 2.7072 | 1.7699 | 400 | 2.7067 |
57
+ | 2.3127 | 1.9912 | 450 | 2.6800 |
58
+ | 2.0786 | 2.2124 | 500 | 2.6677 |
59
+ | 1.9055 | 2.4336 | 550 | 2.5482 |
60
+ | 2.0272 | 2.6549 | 600 | 2.2344 |
61
+ | 1.6753 | 2.8761 | 650 | 2.3265 |
62
+ | 1.4848 | 3.0973 | 700 | 2.5170 |
63
+ | 1.4359 | 3.3186 | 750 | 2.4527 |
64
+ | 1.2884 | 3.5398 | 800 | 2.4033 |
65
+ | 1.3217 | 3.7611 | 850 | 2.0981 |
66
+ | 1.3359 | 3.9823 | 900 | 2.2481 |
67
+ | 0.9068 | 4.2035 | 950 | 2.4053 |
68
+ | 1.1537 | 4.4248 | 1000 | 2.5739 |
69
+ | 0.8742 | 4.6460 | 1050 | 2.5003 |
70
+ | 0.9135 | 4.8673 | 1100 | 2.5511 |
71
+ | 0.9073 | 5.0885 | 1150 | 2.6724 |
72
+ | 0.6596 | 5.3097 | 1200 | 2.6174 |
73
+ | 0.7797 | 5.5310 | 1250 | 2.8350 |
74
+ | 0.6031 | 5.7522 | 1300 | 3.1642 |
75
+ | 0.7287 | 5.9735 | 1350 | 3.0317 |
76
+ | 0.4586 | 6.1947 | 1400 | 3.1821 |
77
+ | 0.5755 | 6.4159 | 1450 | 3.1222 |
78
+ | 0.4174 | 6.6372 | 1500 | 3.6997 |
79
+ | 0.2839 | 6.8584 | 1550 | 3.7044 |
80
+ | 0.5378 | 7.0796 | 1600 | 3.4223 |
81
+ | 0.3549 | 7.3009 | 1650 | 3.3740 |
82
+ | 0.2239 | 7.5221 | 1700 | 3.6018 |
83
+ | 0.3209 | 7.7434 | 1750 | 3.3689 |
84
+ | 0.2594 | 7.9646 | 1800 | 3.6625 |
85
+ | 0.1606 | 8.1858 | 1850 | 3.6916 |
86
+ | 0.1525 | 8.4071 | 1900 | 3.6299 |
87
+ | 0.1104 | 8.6283 | 1950 | 3.7133 |
88
+ | 0.3046 | 8.8496 | 2000 | 3.7701 |
89
+ | 0.3161 | 9.0708 | 2050 | 3.6224 |
90
+ | 0.1331 | 9.2920 | 2100 | 3.6198 |
91
+ | 0.2595 | 9.5133 | 2150 | 3.6251 |
92
+ | 0.1928 | 9.7345 | 2200 | 3.6359 |
93
+ | 0.1465 | 9.9558 | 2250 | 3.6446 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.42.4
99
+ - Pytorch 2.3.1+cu121
100
+ - Datasets 2.20.0
101
+ - Tokenizers 0.19.1