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
2be15b5
•
1 Parent(s): 5e1d919

Upload TFLayoutLMForTokenClassification

Browse files
Files changed (2) hide show
  1. README.md +14 -14
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2389
18
- - Validation Loss: 0.6400
19
- - Train Overall Precision: 0.7230
20
- - Train Overall Recall: 0.8043
21
- - Train Overall F1: 0.7615
22
- - Train Overall Accuracy: 0.8148
23
  - Epoch: 7
24
 
25
  ## Model description
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
46
 
47
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
48
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
49
- | 1.7183 | 1.4293 | 0.2640 | 0.3026 | 0.2820 | 0.5238 | 0 |
50
- | 1.1796 | 0.8384 | 0.5923 | 0.6197 | 0.6057 | 0.7476 | 1 |
51
- | 0.7602 | 0.7016 | 0.6719 | 0.7511 | 0.7093 | 0.7798 | 2 |
52
- | 0.5549 | 0.6367 | 0.6847 | 0.7637 | 0.7220 | 0.7949 | 3 |
53
- | 0.4399 | 0.6261 | 0.7078 | 0.7863 | 0.7449 | 0.8077 | 4 |
54
- | 0.3561 | 0.6431 | 0.7204 | 0.7757 | 0.7470 | 0.8067 | 5 |
55
- | 0.2843 | 0.6247 | 0.7359 | 0.8038 | 0.7683 | 0.8182 | 6 |
56
- | 0.2389 | 0.6400 | 0.7230 | 0.8043 | 0.7615 | 0.8148 | 7 |
57
 
58
 
59
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.2493
18
+ - Validation Loss: 0.6923
19
+ - Train Overall Precision: 0.7272
20
+ - Train Overall Recall: 0.8013
21
+ - Train Overall F1: 0.7625
22
+ - Train Overall Accuracy: 0.8013
23
  - Epoch: 7
24
 
25
  ## Model description
 
46
 
47
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
48
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
49
+ | 1.7180 | 1.4598 | 0.2174 | 0.2454 | 0.2306 | 0.4688 | 0 |
50
+ | 1.1897 | 0.9029 | 0.5570 | 0.6673 | 0.6072 | 0.7282 | 1 |
51
+ | 0.7789 | 0.7082 | 0.6413 | 0.7401 | 0.6872 | 0.7701 | 2 |
52
+ | 0.5964 | 0.6498 | 0.6840 | 0.7647 | 0.7221 | 0.7926 | 3 |
53
+ | 0.4653 | 0.6611 | 0.7031 | 0.7737 | 0.7367 | 0.7890 | 4 |
54
+ | 0.3663 | 0.6544 | 0.7159 | 0.8028 | 0.7569 | 0.8027 | 5 |
55
+ | 0.3010 | 0.6662 | 0.7274 | 0.7913 | 0.7580 | 0.8034 | 6 |
56
+ | 0.2493 | 0.6923 | 0.7272 | 0.8013 | 0.7625 | 0.8013 | 7 |
57
 
58
 
59
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6cf8507f0eb0b62576ca25e67bbb27a53011fba275bc635e067b84ad127e346
3
  size 450829256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4573382e96c8c1f99e1be077519df9701e669be5d441e31c763f2fe7495269d7
3
  size 450829256