Hugging Face's logo

jiy03150
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
PyTorch
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Community
jiy03150 commited on
Commit
6213b82
•
1 Parent(s): 7a382a3

End of training

Browse files
Files changed (2) hide show
  1. README.md +146 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 4.3701
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: 20
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 5.3439 | 0.22 | 50 | 4.6661 |
50
+ | 4.4287 | 0.44 | 100 | 4.2125 |
51
+ | 4.0781 | 0.66 | 150 | 3.7145 |
52
+ | 3.8419 | 0.88 | 200 | 3.5926 |
53
+ | 3.633 | 1.11 | 250 | 3.4266 |
54
+ | 3.1492 | 1.33 | 300 | 3.2833 |
55
+ | 3.2018 | 1.55 | 350 | 3.0237 |
56
+ | 2.8891 | 1.77 | 400 | 2.9976 |
57
+ | 2.6695 | 1.99 | 450 | 3.0654 |
58
+ | 2.211 | 2.21 | 500 | 2.7658 |
59
+ | 2.2555 | 2.43 | 550 | 2.5009 |
60
+ | 2.0293 | 2.65 | 600 | 2.3515 |
61
+ | 1.8663 | 2.88 | 650 | 2.1264 |
62
+ | 1.6332 | 3.1 | 700 | 2.3934 |
63
+ | 1.5298 | 3.32 | 750 | 2.6686 |
64
+ | 1.3594 | 3.54 | 800 | 2.0781 |
65
+ | 1.3923 | 3.76 | 850 | 2.2174 |
66
+ | 1.26 | 3.98 | 900 | 2.5728 |
67
+ | 0.9371 | 4.2 | 950 | 2.7164 |
68
+ | 0.9891 | 4.42 | 1000 | 2.8637 |
69
+ | 1.0822 | 4.65 | 1050 | 2.5435 |
70
+ | 0.9355 | 4.87 | 1100 | 2.7256 |
71
+ | 0.9527 | 5.09 | 1150 | 2.8934 |
72
+ | 0.9454 | 5.31 | 1200 | 3.0235 |
73
+ | 0.6458 | 5.53 | 1250 | 3.2280 |
74
+ | 0.8697 | 5.75 | 1300 | 2.8636 |
75
+ | 0.9365 | 5.97 | 1350 | 2.8955 |
76
+ | 0.4425 | 6.19 | 1400 | 3.0859 |
77
+ | 0.6329 | 6.42 | 1450 | 3.0695 |
78
+ | 0.7564 | 6.64 | 1500 | 2.5050 |
79
+ | 0.5747 | 6.86 | 1550 | 3.2825 |
80
+ | 0.5451 | 7.08 | 1600 | 3.4123 |
81
+ | 0.5432 | 7.3 | 1650 | 3.1163 |
82
+ | 0.3738 | 7.52 | 1700 | 2.8969 |
83
+ | 0.5026 | 7.74 | 1750 | 2.8579 |
84
+ | 0.4245 | 7.96 | 1800 | 3.2212 |
85
+ | 0.3145 | 8.19 | 1850 | 3.4482 |
86
+ | 0.516 | 8.41 | 1900 | 2.9995 |
87
+ | 0.2816 | 8.63 | 1950 | 2.9903 |
88
+ | 0.3946 | 8.85 | 2000 | 3.3378 |
89
+ | 0.3854 | 9.07 | 2050 | 3.4644 |
90
+ | 0.2191 | 9.29 | 2100 | 3.5034 |
91
+ | 0.3854 | 9.51 | 2150 | 3.4320 |
92
+ | 0.2207 | 9.73 | 2200 | 3.6972 |
93
+ | 0.2779 | 9.96 | 2250 | 3.6866 |
94
+ | 0.2837 | 10.18 | 2300 | 3.8988 |
95
+ | 0.1613 | 10.4 | 2350 | 3.8722 |
96
+ | 0.1069 | 10.62 | 2400 | 3.9079 |
97
+ | 0.4031 | 10.84 | 2450 | 3.5352 |
98
+ | 0.2129 | 11.06 | 2500 | 3.6764 |
99
+ | 0.1166 | 11.28 | 2550 | 4.1964 |
100
+ | 0.1599 | 11.5 | 2600 | 4.2577 |
101
+ | 0.2108 | 11.73 | 2650 | 3.7519 |
102
+ | 0.3207 | 11.95 | 2700 | 3.6609 |
103
+ | 0.2291 | 12.17 | 2750 | 3.5265 |
104
+ | 0.1609 | 12.39 | 2800 | 3.8727 |
105
+ | 0.2308 | 12.61 | 2850 | 3.9877 |
106
+ | 0.1461 | 12.83 | 2900 | 4.0395 |
107
+ | 0.1353 | 13.05 | 2950 | 3.8678 |
108
+ | 0.0735 | 13.27 | 3000 | 3.9054 |
109
+ | 0.1695 | 13.5 | 3050 | 3.5661 |
110
+ | 0.0129 | 13.72 | 3100 | 3.9625 |
111
+ | 0.1691 | 13.94 | 3150 | 3.7996 |
112
+ | 0.066 | 14.16 | 3200 | 4.2540 |
113
+ | 0.0484 | 14.38 | 3250 | 4.0625 |
114
+ | 0.099 | 14.6 | 3300 | 4.4666 |
115
+ | 0.127 | 14.82 | 3350 | 4.0762 |
116
+ | 0.046 | 15.04 | 3400 | 4.1859 |
117
+ | 0.0608 | 15.27 | 3450 | 4.4004 |
118
+ | 0.1002 | 15.49 | 3500 | 4.3228 |
119
+ | 0.0394 | 15.71 | 3550 | 4.4576 |
120
+ | 0.0863 | 15.93 | 3600 | 4.4386 |
121
+ | 0.0214 | 16.15 | 3650 | 4.5233 |
122
+ | 0.0661 | 16.37 | 3700 | 4.4493 |
123
+ | 0.0448 | 16.59 | 3750 | 4.3361 |
124
+ | 0.0463 | 16.81 | 3800 | 4.4174 |
125
+ | 0.0456 | 17.04 | 3850 | 4.4851 |
126
+ | 0.0144 | 17.26 | 3900 | 4.4655 |
127
+ | 0.0268 | 17.48 | 3950 | 4.4417 |
128
+ | 0.0529 | 17.7 | 4000 | 4.3580 |
129
+ | 0.0678 | 17.92 | 4050 | 4.2008 |
130
+ | 0.0039 | 18.14 | 4100 | 4.2346 |
131
+ | 0.0481 | 18.36 | 4150 | 4.2652 |
132
+ | 0.0501 | 18.58 | 4200 | 4.2786 |
133
+ | 0.0271 | 18.81 | 4250 | 4.2857 |
134
+ | 0.0322 | 19.03 | 4300 | 4.3047 |
135
+ | 0.0187 | 19.25 | 4350 | 4.3691 |
136
+ | 0.0469 | 19.47 | 4400 | 4.3560 |
137
+ | 0.0056 | 19.69 | 4450 | 4.3626 |
138
+ | 0.0099 | 19.91 | 4500 | 4.3701 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.35.0.dev0
144
+ - Pytorch 2.0.1+cu118
145
+ - Datasets 2.14.5
146
+ - Tokenizers 0.14.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f2309debb511b8611c76e90d6b7452dd4f0d78f96ccd42c43a7faf1891472b
3
  size 802214001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a780892067cade8fba347980f40e418441a98b98c2cb62221894d8b12be0b4
3
  size 802214001