Hugging Face's logo

sahil-everlign
/
layoutlmv2-base-uncased_finetuned_docvqa_on_1200

Document Question Answering
Transformers
TensorBoard
Safetensors
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sahil-everlign commited on
Commit
9a66d54
•
1 Parent(s): 4b5e0de

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_on_1200
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_on_1200
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: 4.6669
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
+ | 5.26 | 0.2212 | 50 | 4.5357 |
51
+ | 4.3552 | 0.4425 | 100 | 4.0284 |
52
+ | 4.0237 | 0.6637 | 150 | 3.7961 |
53
+ | 3.7428 | 0.8850 | 200 | 3.5727 |
54
+ | 3.6213 | 1.1062 | 250 | 3.7866 |
55
+ | 3.2334 | 1.3274 | 300 | 3.1121 |
56
+ | 3.0382 | 1.5487 | 350 | 2.9537 |
57
+ | 2.8353 | 1.7699 | 400 | 2.8318 |
58
+ | 2.4759 | 1.9912 | 450 | 2.6736 |
59
+ | 1.9881 | 2.2124 | 500 | 3.0365 |
60
+ | 1.9279 | 2.4336 | 550 | 2.4144 |
61
+ | 1.9336 | 2.6549 | 600 | 2.1754 |
62
+ | 1.772 | 2.8761 | 650 | 2.1086 |
63
+ | 1.5504 | 3.0973 | 700 | 2.7056 |
64
+ | 1.4621 | 3.3186 | 750 | 2.8930 |
65
+ | 1.4227 | 3.5398 | 800 | 2.4620 |
66
+ | 1.3924 | 3.7611 | 850 | 2.1275 |
67
+ | 1.3063 | 3.9823 | 900 | 2.2443 |
68
+ | 1.0697 | 4.2035 | 950 | 2.6747 |
69
+ | 0.9476 | 4.4248 | 1000 | 2.7229 |
70
+ | 1.0868 | 4.6460 | 1050 | 2.9257 |
71
+ | 0.8726 | 4.8673 | 1100 | 2.7007 |
72
+ | 0.9436 | 5.0885 | 1150 | 2.8765 |
73
+ | 0.7219 | 5.3097 | 1200 | 2.5301 |
74
+ | 0.6919 | 5.5310 | 1250 | 2.9763 |
75
+ | 0.491 | 5.7522 | 1300 | 3.1198 |
76
+ | 0.5382 | 5.9735 | 1350 | 3.0883 |
77
+ | 0.462 | 6.1947 | 1400 | 3.2955 |
78
+ | 0.6533 | 6.4159 | 1450 | 3.3370 |
79
+ | 0.6477 | 6.6372 | 1500 | 3.3794 |
80
+ | 0.4849 | 6.8584 | 1550 | 3.3798 |
81
+ | 0.4881 | 7.0796 | 1600 | 3.2085 |
82
+ | 0.3952 | 7.3009 | 1650 | 3.2885 |
83
+ | 0.161 | 7.5221 | 1700 | 3.6201 |
84
+ | 0.6895 | 7.7434 | 1750 | 3.4253 |
85
+ | 0.4638 | 7.9646 | 1800 | 3.4787 |
86
+ | 0.2186 | 8.1858 | 1850 | 3.7668 |
87
+ | 0.2531 | 8.4071 | 1900 | 3.7723 |
88
+ | 0.3971 | 8.6283 | 1950 | 3.7131 |
89
+ | 0.5665 | 8.8496 | 2000 | 3.5627 |
90
+ | 0.3377 | 9.0708 | 2050 | 3.1885 |
91
+ | 0.208 | 9.2920 | 2100 | 3.3734 |
92
+ | 0.1775 | 9.5133 | 2150 | 4.0609 |
93
+ | 0.3295 | 9.7345 | 2200 | 3.7039 |
94
+ | 0.2627 | 9.9558 | 2250 | 3.6028 |
95
+ | 0.1988 | 10.1770 | 2300 | 3.6288 |
96
+ | 0.1772 | 10.3982 | 2350 | 3.5394 |
97
+ | 0.0719 | 10.6195 | 2400 | 4.2068 |
98
+ | 0.1629 | 10.8407 | 2450 | 4.2701 |
99
+ | 0.1921 | 11.0619 | 2500 | 4.0440 |
100
+ | 0.164 | 11.2832 | 2550 | 3.9099 |
101
+ | 0.1281 | 11.5044 | 2600 | 3.7753 |
102
+ | 0.0586 | 11.7257 | 2650 | 3.9491 |
103
+ | 0.1436 | 11.9469 | 2700 | 4.2734 |
104
+ | 0.0405 | 12.1681 | 2750 | 4.4347 |
105
+ | 0.0664 | 12.3894 | 2800 | 4.2338 |
106
+ | 0.0864 | 12.6106 | 2850 | 3.8694 |
107
+ | 0.103 | 12.8319 | 2900 | 3.9883 |
108
+ | 0.0456 | 13.0531 | 2950 | 4.5064 |
109
+ | 0.05 | 13.2743 | 3000 | 4.1434 |
110
+ | 0.0436 | 13.4956 | 3050 | 4.3928 |
111
+ | 0.0798 | 13.7168 | 3100 | 4.5576 |
112
+ | 0.0919 | 13.9381 | 3150 | 4.4114 |
113
+ | 0.0988 | 14.1593 | 3200 | 4.4998 |
114
+ | 0.0332 | 14.3805 | 3250 | 4.3948 |
115
+ | 0.0326 | 14.6018 | 3300 | 4.3823 |
116
+ | 0.0434 | 14.8230 | 3350 | 4.2468 |
117
+ | 0.0926 | 15.0442 | 3400 | 4.3909 |
118
+ | 0.027 | 15.2655 | 3450 | 4.5539 |
119
+ | 0.047 | 15.4867 | 3500 | 4.5799 |
120
+ | 0.0189 | 15.7080 | 3550 | 4.3943 |
121
+ | 0.0096 | 15.9292 | 3600 | 4.4218 |
122
+ | 0.0467 | 16.1504 | 3650 | 4.6181 |
123
+ | 0.0144 | 16.3717 | 3700 | 4.5609 |
124
+ | 0.0339 | 16.5929 | 3750 | 4.5994 |
125
+ | 0.074 | 16.8142 | 3800 | 4.5598 |
126
+ | 0.018 | 17.0354 | 3850 | 4.5528 |
127
+ | 0.0043 | 17.2566 | 3900 | 4.6133 |
128
+ | 0.0179 | 17.4779 | 3950 | 4.5414 |
129
+ | 0.039 | 17.6991 | 4000 | 4.4690 |
130
+ | 0.0134 | 17.9204 | 4050 | 4.4789 |
131
+ | 0.0094 | 18.1416 | 4100 | 4.5317 |
132
+ | 0.004 | 18.3628 | 4150 | 4.5711 |
133
+ | 0.0064 | 18.5841 | 4200 | 4.6237 |
134
+ | 0.0505 | 18.8053 | 4250 | 4.6148 |
135
+ | 0.0312 | 19.0265 | 4300 | 4.6302 |
136
+ | 0.0127 | 19.2478 | 4350 | 4.6577 |
137
+ | 0.0169 | 19.4690 | 4400 | 4.6685 |
138
+ | 0.0192 | 19.6903 | 4450 | 4.6626 |
139
+ | 0.0232 | 19.9115 | 4500 | 4.6669 |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - Transformers 4.44.2
145
+ - Pytorch 2.4.1+cu121
146
+ - Datasets 3.0.1
147
+ - Tokenizers 0.19.1