Hugging Face's logo

stevethecur
/
layoutlm-funsd-tf

Token Classification
Transformers
TensorFlow
TensorBoard
layoutlm
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
stevethecur commited on
Commit
f988475
•
1 Parent(s): 872aa7f

Upload TFLayoutLMForTokenClassification

Browse files
Files changed (2) hide show
  1. README.md +15 -15
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_keras_callback
5
- base_model: microsoft/layoutlm-base-uncased
6
  model-index:
7
  - name: layoutlm-funsd-tf
8
  results: []
@@ -15,12 +15,12 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.5847
19
- - Validation Loss: 1.1733
20
- - Train Overall Precision: 0.4918
21
- - Train Overall Recall: 0.6026
22
- - Train Overall F1: 0.5416
23
- - Train Overall Accuracy: 0.6392
24
  - Epoch: 7
25
 
26
  ## Model description
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
47
 
48
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
49
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
50
- | 1.7553 | 1.6258 | 0.2306 | 0.1134 | 0.1520 | 0.3303 | 0 |
51
- | 1.4401 | 1.3407 | 0.2930 | 0.4797 | 0.3638 | 0.4365 | 1 |
52
- | 1.2104 | 1.2996 | 0.3092 | 0.4977 | 0.3815 | 0.4740 | 2 |
53
- | 1.0651 | 1.0411 | 0.3652 | 0.5233 | 0.4302 | 0.5949 | 3 |
54
- | 0.9605 | 0.9755 | 0.4209 | 0.5329 | 0.4703 | 0.6064 | 4 |
55
- | 0.8846 | 1.0042 | 0.4473 | 0.5620 | 0.4981 | 0.6270 | 5 |
56
- | 0.7200 | 0.9883 | 0.4845 | 0.5720 | 0.5246 | 0.6381 | 6 |
57
- | 0.5847 | 1.1733 | 0.4918 | 0.6026 | 0.5416 | 0.6392 | 7 |
58
 
59
 
60
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: microsoft/layoutlm-base-uncased
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: layoutlm-funsd-tf
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.6138
19
+ - Validation Loss: 1.0719
20
+ - Train Overall Precision: 0.4799
21
+ - Train Overall Recall: 0.5926
22
+ - Train Overall F1: 0.5303
23
+ - Train Overall Accuracy: 0.6254
24
  - Epoch: 7
25
 
26
  ## Model description
 
47
 
48
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
49
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
50
+ | 1.6621 | 1.4563 | 0.1960 | 0.3126 | 0.2410 | 0.4075 | 0 |
51
+ | 1.3485 | 1.2456 | 0.2943 | 0.4867 | 0.3668 | 0.4838 | 1 |
52
+ | 1.1546 | 1.1675 | 0.3643 | 0.5334 | 0.4329 | 0.5295 | 2 |
53
+ | 1.0163 | 1.0992 | 0.4061 | 0.5514 | 0.4678 | 0.5842 | 3 |
54
+ | 0.8892 | 1.0781 | 0.4346 | 0.5605 | 0.4896 | 0.5989 | 4 |
55
+ | 0.7755 | 1.1893 | 0.4589 | 0.5735 | 0.5098 | 0.5913 | 5 |
56
+ | 0.6631 | 1.0950 | 0.4863 | 0.5595 | 0.5203 | 0.6265 | 6 |
57
+ | 0.6138 | 1.0719 | 0.4799 | 0.5926 | 0.5303 | 0.6254 | 7 |
58
 
59
 
60
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb17e7bbc1ddb91b0c4a2b756c57d6b59cf68a1bc75bb37b4ef64e004c28324b
3
  size 450829256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a3a40e59c97db04b2eae28925c47d43185f0742fceec8eb8a30189f8954937
3
  size 450829256