Hugging Face's logo

vkrnsn
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
Safetensors
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Community
vkrnsn commited on
Commit
a70abc5
•
1 Parent(s): 11165fa

End of training

Browse files
Files changed (1) hide show
  1. README.md +147 -3
README.md CHANGED
@@ -1,3 +1,147 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 4.7623
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
+ | 5.2477 | 0.2212 | 50 | 4.4955 |
51
+ | 4.4322 | 0.4425 | 100 | 4.0859 |
52
+ | 4.2098 | 0.6637 | 150 | 3.8177 |
53
+ | 3.8664 | 0.8850 | 200 | 3.5806 |
54
+ | 3.5251 | 1.1062 | 250 | 3.5032 |
55
+ | 3.1732 | 1.3274 | 300 | 3.2472 |
56
+ | 3.0841 | 1.5487 | 350 | 3.0947 |
57
+ | 2.8536 | 1.7699 | 400 | 2.7800 |
58
+ | 2.4276 | 1.9912 | 450 | 2.7769 |
59
+ | 2.06 | 2.2124 | 500 | 2.6578 |
60
+ | 1.8173 | 2.4336 | 550 | 2.6715 |
61
+ | 2.1107 | 2.6549 | 600 | 2.5620 |
62
+ | 2.1352 | 2.8761 | 650 | 2.3209 |
63
+ | 1.5368 | 3.0973 | 700 | 2.2305 |
64
+ | 1.3107 | 3.3186 | 750 | 2.6482 |
65
+ | 1.4519 | 3.5398 | 800 | 2.3794 |
66
+ | 1.2756 | 3.7611 | 850 | 2.3672 |
67
+ | 1.2282 | 3.9823 | 900 | 2.2342 |
68
+ | 1.0882 | 4.2035 | 950 | 2.7453 |
69
+ | 0.9957 | 4.4248 | 1000 | 2.7899 |
70
+ | 1.0055 | 4.6460 | 1050 | 2.7979 |
71
+ | 0.9377 | 4.8673 | 1100 | 2.5045 |
72
+ | 1.0285 | 5.0885 | 1150 | 2.4579 |
73
+ | 0.6299 | 5.3097 | 1200 | 2.7204 |
74
+ | 0.8789 | 5.5310 | 1250 | 2.6098 |
75
+ | 0.5642 | 5.7522 | 1300 | 2.7831 |
76
+ | 0.6949 | 5.9735 | 1350 | 3.0893 |
77
+ | 0.4063 | 6.1947 | 1400 | 2.8284 |
78
+ | 0.5117 | 6.4159 | 1450 | 3.0634 |
79
+ | 0.4416 | 6.6372 | 1500 | 3.3999 |
80
+ | 0.4999 | 6.8584 | 1550 | 3.2898 |
81
+ | 0.5086 | 7.0796 | 1600 | 3.4221 |
82
+ | 0.3996 | 7.3009 | 1650 | 3.0418 |
83
+ | 0.235 | 7.5221 | 1700 | 3.3613 |
84
+ | 0.4907 | 7.7434 | 1750 | 3.1062 |
85
+ | 0.3033 | 7.9646 | 1800 | 4.0306 |
86
+ | 0.3901 | 8.1858 | 1850 | 3.8258 |
87
+ | 0.3625 | 8.4071 | 1900 | 3.2560 |
88
+ | 0.3074 | 8.6283 | 1950 | 3.6874 |
89
+ | 0.3582 | 8.8496 | 2000 | 3.2337 |
90
+ | 0.2091 | 9.0708 | 2050 | 3.2660 |
91
+ | 0.2416 | 9.2920 | 2100 | 3.4408 |
92
+ | 0.1241 | 9.5133 | 2150 | 3.6883 |
93
+ | 0.2945 | 9.7345 | 2200 | 3.5552 |
94
+ | 0.2575 | 9.9558 | 2250 | 3.3925 |
95
+ | 0.258 | 10.1770 | 2300 | 3.8662 |
96
+ | 0.1662 | 10.3982 | 2350 | 3.6742 |
97
+ | 0.1491 | 10.6195 | 2400 | 4.3579 |
98
+ | 0.2379 | 10.8407 | 2450 | 4.1496 |
99
+ | 0.0899 | 11.0619 | 2500 | 4.2631 |
100
+ | 0.026 | 11.2832 | 2550 | 4.3676 |
101
+ | 0.1356 | 11.5044 | 2600 | 4.1160 |
102
+ | 0.0734 | 11.7257 | 2650 | 3.8254 |
103
+ | 0.2507 | 11.9469 | 2700 | 3.9717 |
104
+ | 0.1241 | 12.1681 | 2750 | 3.7671 |
105
+ | 0.0207 | 12.3894 | 2800 | 3.9668 |
106
+ | 0.0662 | 12.6106 | 2850 | 4.0811 |
107
+ | 0.1262 | 12.8319 | 2900 | 3.9894 |
108
+ | 0.0483 | 13.0531 | 2950 | 4.0627 |
109
+ | 0.0889 | 13.2743 | 3000 | 4.1365 |
110
+ | 0.0311 | 13.4956 | 3050 | 4.1390 |
111
+ | 0.0992 | 13.7168 | 3100 | 4.0020 |
112
+ | 0.1021 | 13.9381 | 3150 | 3.8962 |
113
+ | 0.109 | 14.1593 | 3200 | 4.2122 |
114
+ | 0.0164 | 14.3805 | 3250 | 4.3584 |
115
+ | 0.0663 | 14.6018 | 3300 | 4.1452 |
116
+ | 0.0702 | 14.8230 | 3350 | 4.2793 |
117
+ | 0.0435 | 15.0442 | 3400 | 4.3782 |
118
+ | 0.0504 | 15.2655 | 3450 | 4.3851 |
119
+ | 0.0185 | 15.4867 | 3500 | 4.6016 |
120
+ | 0.0795 | 15.7080 | 3550 | 4.5381 |
121
+ | 0.049 | 15.9292 | 3600 | 4.2093 |
122
+ | 0.0608 | 16.1504 | 3650 | 4.3391 |
123
+ | 0.0953 | 16.3717 | 3700 | 4.2657 |
124
+ | 0.0603 | 16.5929 | 3750 | 4.4624 |
125
+ | 0.0312 | 16.8142 | 3800 | 4.3063 |
126
+ | 0.0038 | 17.0354 | 3850 | 4.4603 |
127
+ | 0.0271 | 17.2566 | 3900 | 4.4354 |
128
+ | 0.0094 | 17.4779 | 3950 | 4.6563 |
129
+ | 0.019 | 17.6991 | 4000 | 4.7925 |
130
+ | 0.045 | 17.9204 | 4050 | 4.6123 |
131
+ | 0.0112 | 18.1416 | 4100 | 4.6376 |
132
+ | 0.0348 | 18.3628 | 4150 | 4.6756 |
133
+ | 0.0216 | 18.5841 | 4200 | 4.7026 |
134
+ | 0.009 | 18.8053 | 4250 | 4.7217 |
135
+ | 0.0356 | 19.0265 | 4300 | 4.7260 |
136
+ | 0.0479 | 19.2478 | 4350 | 4.7143 |
137
+ | 0.0114 | 19.4690 | 4400 | 4.7547 |
138
+ | 0.0069 | 19.6903 | 4450 | 4.7605 |
139
+ | 0.0053 | 19.9115 | 4500 | 4.7623 |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - Transformers 4.44.2
145
+ - Pytorch 2.5.0+cu121
146
+ - Datasets 3.0.2
147
+ - Tokenizers 0.19.1