Hugging Face's logo

cor-c
/
layoutlmv3-finetuned-cord_100

Token Classification
Transformers
TensorBoard
Safetensors
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
cor-c commited on
Commit
0a4e8e6
•
1 Parent(s): ed58430

layoutlmv3-finetuned-cord_100

Browse files
Files changed (3) hide show
  1. README.md +27 -27
  2. model.safetensors +1 -1
  3. runs/Apr14_18-17-26_1d3eb57a3be8/events.out.tfevents.1713118660.1d3eb57a3be8.653.0 +2 -2
README.md CHANGED
@@ -4,7 +4,7 @@ base_model: microsoft/layoutlmv3-base
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - cord-layoutlmv3
8
  metrics:
9
  - precision
10
  - recall
@@ -17,24 +17,24 @@ model-index:
17
  name: Token Classification
18
  type: token-classification
19
  dataset:
20
- name: cord-layoutlmv3
21
- type: cord-layoutlmv3
22
  config: cord
23
  split: test
24
  args: cord
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9266666666666666
29
  - name: Recall
30
  type: recall
31
- value: 0.936377245508982
32
  - name: F1
33
  type: f1
34
- value: 0.9314966492926285
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9354838709677419
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  # layoutlmv3-finetuned-cord_100
44
 
45
- This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.3194
48
- - Precision: 0.9267
49
- - Recall: 0.9364
50
- - F1: 0.9315
51
- - Accuracy: 0.9355
52
 
53
  ## Model description
54
 
@@ -79,21 +79,21 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 4.17 | 250 | 1.0054 | 0.7555 | 0.8024 | 0.7782 | 0.8081 |
83
- | 1.4019 | 8.33 | 500 | 0.5287 | 0.8320 | 0.8638 | 0.8476 | 0.8739 |
84
- | 1.4019 | 12.5 | 750 | 0.3790 | 0.9043 | 0.9192 | 0.9117 | 0.9236 |
85
- | 0.3185 | 16.67 | 1000 | 0.3253 | 0.9178 | 0.9281 | 0.9230 | 0.9355 |
86
- | 0.3185 | 20.83 | 1250 | 0.3231 | 0.9223 | 0.9334 | 0.9278 | 0.9304 |
87
- | 0.1319 | 25.0 | 1500 | 0.3039 | 0.9317 | 0.9394 | 0.9355 | 0.9419 |
88
- | 0.1319 | 29.17 | 1750 | 0.3142 | 0.9287 | 0.9364 | 0.9325 | 0.9334 |
89
- | 0.0725 | 33.33 | 2000 | 0.2982 | 0.9296 | 0.9386 | 0.9341 | 0.9419 |
90
- | 0.0725 | 37.5 | 2250 | 0.3189 | 0.9288 | 0.9371 | 0.9329 | 0.9346 |
91
- | 0.0549 | 41.67 | 2500 | 0.3194 | 0.9267 | 0.9364 | 0.9315 | 0.9355 |
92
 
93
 
94
  ### Framework versions
95
 
96
- - Transformers 4.36.2
97
- - Pytorch 2.1.0+cu121
98
- - Datasets 2.16.1
99
- - Tokenizers 0.15.0
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - layoutlm_v3
8
  metrics:
9
  - precision
10
  - recall
 
17
  name: Token Classification
18
  type: token-classification
19
  dataset:
20
+ name: layoutlm_v3
21
+ type: layoutlm_v3
22
  config: cord
23
  split: test
24
  args: cord
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9297856614929786
29
  - name: Recall
30
  type: recall
31
+ value: 0.9416167664670658
32
  - name: F1
33
  type: f1
34
+ value: 0.9356638155448121
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9393039049235993
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
42
 
43
  # layoutlmv3-finetuned-cord_100
44
 
45
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the layoutlm_v3 dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.2976
48
+ - Precision: 0.9298
49
+ - Recall: 0.9416
50
+ - F1: 0.9357
51
+ - Accuracy: 0.9393
52
 
53
  ## Model description
54
 
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 4.17 | 250 | 1.0222 | 0.7468 | 0.7949 | 0.7701 | 0.8014 |
83
+ | 1.3962 | 8.33 | 500 | 0.5292 | 0.8414 | 0.8735 | 0.8571 | 0.8778 |
84
+ | 1.3962 | 12.5 | 750 | 0.3844 | 0.9049 | 0.9192 | 0.9120 | 0.9249 |
85
+ | 0.335 | 16.67 | 1000 | 0.3302 | 0.9243 | 0.9326 | 0.9285 | 0.9342 |
86
+ | 0.335 | 20.83 | 1250 | 0.3062 | 0.9204 | 0.9349 | 0.9276 | 0.9406 |
87
+ | 0.1419 | 25.0 | 1500 | 0.2931 | 0.9268 | 0.9386 | 0.9327 | 0.9414 |
88
+ | 0.1419 | 29.17 | 1750 | 0.2925 | 0.9248 | 0.9386 | 0.9316 | 0.9359 |
89
+ | 0.0801 | 33.33 | 2000 | 0.2963 | 0.9276 | 0.9394 | 0.9334 | 0.9359 |
90
+ | 0.0801 | 37.5 | 2250 | 0.2916 | 0.9283 | 0.9401 | 0.9342 | 0.9363 |
91
+ | 0.0584 | 41.67 | 2500 | 0.2976 | 0.9298 | 0.9416 | 0.9357 | 0.9393 |
92
 
93
 
94
  ### Framework versions
95
 
96
+ - Transformers 4.39.3
97
+ - Pytorch 2.2.1+cu121
98
+ - Datasets 2.18.0
99
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6687f7bc0567bc87132069a0bd9967eef4bb5f4f6f05a7702d734470f09cd02f
3
  size 503884236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32256f4a328c614d27c2f4eafdff1de48e3b6c51d25afb3facc4c7e9f81a6cc9
3
  size 503884236
runs/Apr14_18-17-26_1d3eb57a3be8/events.out.tfevents.1713118660.1d3eb57a3be8.653.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5abb7e8fbc35e27be954080f1057bd8f2fda7c45abba30407d2169be2f8d4c0c
3
- size 13322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c18d4fa7c9fb69c36b7540f293232888d43aea36b4dad7e2d4d087f8c2f6632
3
+ size 14831