Hugging Face's logo

sreejith8100
/
layoutlm-funsd

Token Classification
Transformers
PyTorch
layoutlm
Generated from Trainer
Model card Files
xet
 Community
sreejith8100 commited on
Commit
2eaa06a
·
1 Parent(s): 0ac19ef

End of training

Browse files
Files changed (2) hide show
  1. README.md +36 -16
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.2761
19
  - Nswer Precision: 1.0
20
  - Nswer Recall: 1.0
21
  - Nswer F1: 1.0
22
- - Nswer Number: 1
23
  - Uestion Precision: 1.0
24
  - Uestion Recall: 1.0
25
  - Uestion F1: 1.0
26
- - Uestion Number: 1
27
  - Overall Precision: 1.0
28
  - Overall Recall: 1.0
29
  - Overall F1: 1.0
@@ -47,27 +47,47 @@ More information needed
47
 
48
  The following hyperparameters were used during training:
49
  - learning_rate: 3e-05
50
- - train_batch_size: 2
51
- - eval_batch_size: 1
52
  - seed: 42
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
- - num_epochs: 10
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Nswer Precision | Nswer Recall | Nswer F1 | Nswer Number | Uestion Precision | Uestion Recall | Uestion F1 | Uestion Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------:|:--------------:|:----------:|:----------------:|
61
- | 0.6584 | 1.0 | 2 | 0.6309 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
62
- | 0.6136 | 2.0 | 4 | 0.5278 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
63
- | 0.5319 | 3.0 | 6 | 0.4607 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
64
- | 0.4728 | 4.0 | 8 | 0.4026 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
65
- | 0.4366 | 5.0 | 10 | 0.3644 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
66
- | 0.4004 | 6.0 | 12 | 0.3341 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
67
- | 0.3601 | 7.0 | 14 | 0.3125 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
68
- | 0.3359 | 8.0 | 16 | 0.2943 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
69
- | 0.3223 | 9.0 | 18 | 0.2817 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
70
- | 0.3144 | 10.0 | 20 | 0.2761 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0112
19
  - Nswer Precision: 1.0
20
  - Nswer Recall: 1.0
21
  - Nswer F1: 1.0
22
+ - Nswer Number: 82
23
  - Uestion Precision: 1.0
24
  - Uestion Recall: 1.0
25
  - Uestion F1: 1.0
26
+ - Uestion Number: 82
27
  - Overall Precision: 1.0
28
  - Overall Recall: 1.0
29
  - Overall F1: 1.0
 
47
 
48
  The following hyperparameters were used during training:
49
  - learning_rate: 3e-05
50
+ - train_batch_size: 8
51
+ - eval_batch_size: 4
52
  - seed: 42
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
+ - num_epochs: 30
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Nswer Precision | Nswer Recall | Nswer F1 | Nswer Number | Uestion Precision | Uestion Recall | Uestion F1 | Uestion Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------------:|:--------------:|:----------:|:----------------:|
61
+ | 0.2402 | 1.0 | 41 | 0.0879 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
62
+ | 0.0874 | 2.0 | 82 | 0.0695 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
63
+ | 0.0718 | 3.0 | 123 | 0.0592 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
64
+ | 0.0617 | 4.0 | 164 | 0.0511 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
65
+ | 0.0537 | 5.0 | 205 | 0.0446 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
66
+ | 0.0473 | 6.0 | 246 | 0.0393 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
67
+ | 0.0421 | 7.0 | 287 | 0.0349 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
68
+ | 0.0379 | 8.0 | 328 | 0.0313 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
69
+ | 0.0343 | 9.0 | 369 | 0.0282 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
70
+ | 0.0313 | 10.0 | 410 | 0.0257 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
71
+ | 0.029 | 11.0 | 451 | 0.0236 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
72
+ | 0.0269 | 12.0 | 492 | 0.0217 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
73
+ | 0.025 | 13.0 | 533 | 0.0201 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
74
+ | 0.0234 | 14.0 | 574 | 0.0188 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
75
+ | 0.022 | 15.0 | 615 | 0.0176 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
76
+ | 0.0209 | 16.0 | 656 | 0.0166 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
77
+ | 0.0199 | 17.0 | 697 | 0.0157 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
78
+ | 0.0191 | 18.0 | 738 | 0.0149 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
79
+ | 0.0184 | 19.0 | 779 | 0.0143 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
80
+ | 0.0177 | 20.0 | 820 | 0.0137 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
81
+ | 0.017 | 21.0 | 861 | 0.0132 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
82
+ | 0.0166 | 22.0 | 902 | 0.0128 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
83
+ | 0.016 | 23.0 | 943 | 0.0124 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
84
+ | 0.0157 | 24.0 | 984 | 0.0121 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
85
+ | 0.0156 | 25.0 | 1025 | 0.0118 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
86
+ | 0.0151 | 26.0 | 1066 | 0.0116 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
87
+ | 0.0151 | 27.0 | 1107 | 0.0114 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
88
+ | 0.0149 | 28.0 | 1148 | 0.0113 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
89
+ | 0.0147 | 29.0 | 1189 | 0.0113 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
90
+ | 0.0147 | 30.0 | 1230 | 0.0112 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 82 | 1.0 | 1.0 | 1.0 | 1.0 |
91
 
92
 
93
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa48bf28702eeeca13871e2b0b04ec0583456e9540b944cb21f7d1a7c14bbc29
3
  size 802210605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f3de5c23a4ebbcc4871b0e7032d4fdeddf3de6e3c1042cb120b808af529baf
3
  size 802210605