Hugging Face's logo

pooh
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
PyTorch
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Community
pooh commited on
Commit
e77527f
•
1 Parent(s): 6a16575

Model save

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: 4.9529
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
+ | 5.2903 | 0.22 | 50 | 4.6096 |
50
+ | 4.441 | 0.44 | 100 | 4.1809 |
51
+ | 4.1512 | 0.66 | 150 | 3.8270 |
52
+ | 3.9297 | 0.88 | 200 | 3.6180 |
53
+ | 3.7006 | 1.11 | 250 | 3.3508 |
54
+ | 3.1238 | 1.33 | 300 | 3.4886 |
55
+ | 3.177 | 1.55 | 350 | 3.0878 |
56
+ | 2.8817 | 1.77 | 400 | 2.8975 |
57
+ | 2.6113 | 1.99 | 450 | 3.1366 |
58
+ | 2.9929 | 2.21 | 500 | 4.2811 |
59
+ | 2.8507 | 2.43 | 550 | 3.1442 |
60
+ | 2.6294 | 2.65 | 600 | 2.7537 |
61
+ | 2.9134 | 2.88 | 650 | 4.0845 |
62
+ | 2.7527 | 3.1 | 700 | 2.6888 |
63
+ | 2.2184 | 3.32 | 750 | 2.6068 |
64
+ | 1.9832 | 3.54 | 800 | 2.3920 |
65
+ | 1.8607 | 3.76 | 850 | 2.3026 |
66
+ | 1.6756 | 3.98 | 900 | 2.4535 |
67
+ | 1.594 | 4.2 | 950 | 2.3539 |
68
+ | 1.3695 | 4.42 | 1000 | 2.9487 |
69
+ | 1.4473 | 4.65 | 1050 | 2.3269 |
70
+ | 1.0998 | 4.87 | 1100 | 2.5812 |
71
+ | 1.043 | 5.09 | 1150 | 2.7785 |
72
+ | 1.0655 | 5.31 | 1200 | 3.1658 |
73
+ | 1.2366 | 5.53 | 1250 | 3.5025 |
74
+ | 1.1033 | 5.75 | 1300 | 3.0308 |
75
+ | 1.1406 | 5.97 | 1350 | 2.4193 |
76
+ | 0.7332 | 6.19 | 1400 | 3.0098 |
77
+ | 0.7752 | 6.42 | 1450 | 3.0226 |
78
+ | 0.9816 | 6.64 | 1500 | 3.1292 |
79
+ | 0.794 | 6.86 | 1550 | 3.4569 |
80
+ | 0.6923 | 7.08 | 1600 | 3.5805 |
81
+ | 0.4034 | 7.3 | 1650 | 3.9237 |
82
+ | 0.4836 | 7.52 | 1700 | 3.4433 |
83
+ | 0.6216 | 7.74 | 1750 | 3.1084 |
84
+ | 0.6027 | 7.96 | 1800 | 3.5491 |
85
+ | 0.4783 | 8.19 | 1850 | 3.7448 |
86
+ | 0.4513 | 8.41 | 1900 | 3.4646 |
87
+ | 0.4544 | 8.63 | 1950 | 3.7954 |
88
+ | 0.5161 | 8.85 | 2000 | 3.7831 |
89
+ | 0.1872 | 9.07 | 2050 | 3.6736 |
90
+ | 0.506 | 9.29 | 2100 | 3.7390 |
91
+ | 0.2257 | 9.51 | 2150 | 3.9423 |
92
+ | 0.2648 | 9.73 | 2200 | 3.7982 |
93
+ | 0.3953 | 9.96 | 2250 | 3.2984 |
94
+ | 0.1601 | 10.18 | 2300 | 3.6460 |
95
+ | 0.2689 | 10.4 | 2350 | 3.9842 |
96
+ | 0.2762 | 10.62 | 2400 | 3.2707 |
97
+ | 0.3091 | 10.84 | 2450 | 3.4759 |
98
+ | 0.2036 | 11.06 | 2500 | 3.7818 |
99
+ | 0.1104 | 11.28 | 2550 | 3.8338 |
100
+ | 0.1555 | 11.5 | 2600 | 3.7824 |
101
+ | 0.2794 | 11.73 | 2650 | 3.7954 |
102
+ | 0.2728 | 11.95 | 2700 | 3.5966 |
103
+ | 0.2168 | 12.17 | 2750 | 4.2583 |
104
+ | 0.1133 | 12.39 | 2800 | 4.3897 |
105
+ | 0.293 | 12.61 | 2850 | 3.9776 |
106
+ | 0.1307 | 12.83 | 2900 | 4.4287 |
107
+ | 0.2012 | 13.05 | 2950 | 4.0434 |
108
+ | 0.1583 | 13.27 | 3000 | 3.8509 |
109
+ | 0.1016 | 13.5 | 3050 | 3.9090 |
110
+ | 0.0329 | 13.72 | 3100 | 4.2917 |
111
+ | 0.1034 | 13.94 | 3150 | 4.3789 |
112
+ | 0.0928 | 14.16 | 3200 | 4.4046 |
113
+ | 0.1318 | 14.38 | 3250 | 4.2611 |
114
+ | 0.1015 | 14.6 | 3300 | 4.4932 |
115
+ | 0.1499 | 14.82 | 3350 | 4.4150 |
116
+ | 0.1858 | 15.04 | 3400 | 4.1948 |
117
+ | 0.1402 | 15.27 | 3450 | 4.3734 |
118
+ | 0.0584 | 15.49 | 3500 | 4.3949 |
119
+ | 0.0288 | 15.71 | 3550 | 4.6144 |
120
+ | 0.0554 | 15.93 | 3600 | 4.8472 |
121
+ | 0.0853 | 16.15 | 3650 | 4.7406 |
122
+ | 0.0111 | 16.37 | 3700 | 5.0774 |
123
+ | 0.1094 | 16.59 | 3750 | 4.9672 |
124
+ | 0.0102 | 16.81 | 3800 | 4.9885 |
125
+ | 0.0884 | 17.04 | 3850 | 5.0612 |
126
+ | 0.0318 | 17.26 | 3900 | 5.1363 |
127
+ | 0.1083 | 17.48 | 3950 | 4.7403 |
128
+ | 0.0891 | 17.7 | 4000 | 4.6907 |
129
+ | 0.0495 | 17.92 | 4050 | 4.7827 |
130
+ | 0.015 | 18.14 | 4100 | 5.0118 |
131
+ | 0.0554 | 18.36 | 4150 | 4.9823 |
132
+ | 0.084 | 18.58 | 4200 | 4.9539 |
133
+ | 0.0714 | 18.81 | 4250 | 4.8877 |
134
+ | 0.0573 | 19.03 | 4300 | 4.9120 |
135
+ | 0.012 | 19.25 | 4350 | 4.9568 |
136
+ | 0.0381 | 19.47 | 4400 | 4.9459 |
137
+ | 0.0126 | 19.69 | 4450 | 4.9544 |
138
+ | 0.0591 | 19.91 | 4500 | 4.9529 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.32.1
144
+ - Pytorch 2.1.0
145
+ - Datasets 2.14.6
146
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9267cc9324aea549e8d003c1f9b350813973ed6dc59740026989105c4512456
3
  size 802214446
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ec2c543c8a16c687e8412b1089e113ab2eac14088bd3c54fefbd7ac9bae489
3
  size 802214446