cor-c commited on
Commit
def5f9c
·
verified ·
1 Parent(s): d65f92e

Upload TFLayoutLMForTokenClassification

Browse files
Files changed (2) hide show
  1. README.md +16 -9
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -4,24 +4,24 @@ base_model: microsoft/layoutlm-base-uncased
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
7
- - name: cor-c/layoutlm-invoice-tf-1
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
  probably proofread and complete it, then remove this comment. -->
13
 
14
- # cor-c/layoutlm-invoice-tf-1
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: 2.4376
19
- - Validation Loss: 2.0394
20
- - Train Overall Precision: 0.0
21
- - Train Overall Recall: 0.0
22
- - Train Overall F1: 0.0
23
- - Train Overall Accuracy: 0.3247
24
- - Epoch: 0
25
 
26
  ## Model description
27
 
@@ -48,6 +48,13 @@ The following hyperparameters were used during training:
48
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
49
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
50
  | 2.4376 | 2.0394 | 0.0 | 0.0 | 0.0 | 0.3247 | 0 |
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
 
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
7
+ - name: layoutlm-invoice-tf-1
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
  probably proofread and complete it, then remove this comment. -->
13
 
14
+ # layoutlm-invoice-tf-1
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: 0.2994
19
+ - Validation Loss: 0.3489
20
+ - Train Overall Precision: 0.5682
21
+ - Train Overall Recall: 0.5668
22
+ - Train Overall F1: 0.5675
23
+ - Train Overall Accuracy: 0.8973
24
+ - Epoch: 7
25
 
26
  ## Model description
27
 
 
48
  | Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
49
  |:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
50
  | 2.4376 | 2.0394 | 0.0 | 0.0 | 0.0 | 0.3247 | 0 |
51
+ | 1.7800 | 1.4827 | 0.0112 | 0.0202 | 0.0144 | 0.5774 | 1 |
52
+ | 1.3231 | 1.0832 | 0.0710 | 0.1008 | 0.0833 | 0.6988 | 2 |
53
+ | 0.9662 | 0.8311 | 0.1626 | 0.2015 | 0.1800 | 0.7421 | 3 |
54
+ | 0.7250 | 0.6259 | 0.2949 | 0.3350 | 0.3137 | 0.8371 | 4 |
55
+ | 0.5245 | 0.4803 | 0.4049 | 0.4131 | 0.4090 | 0.8646 | 5 |
56
+ | 0.3951 | 0.3957 | 0.5206 | 0.5088 | 0.5146 | 0.8892 | 6 |
57
+ | 0.2994 | 0.3489 | 0.5682 | 0.5668 | 0.5675 | 0.8973 | 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:e61cbbe93b2e265e14cebe3656cc1f8187aabbbaffd73bf1d94daf036ce8d264
3
  size 450850760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fbfcad253831ab53b081bfb71bd262b3a382abf40467a692d59e8efec3614a1
3
  size 450850760