Hugging Face's logo

mp-02
/
layoutlmv3-finetuned-funsd

PyTorch
TensorBoard
Safetensors
layoutlmv3
Generated from Trainer
Eval Results
Model card Files Metrics Community
mp-02 commited on
Commit
d34a02d
•
1 Parent(s): 596ce6a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -23
README.md CHANGED
@@ -1,7 +1,8 @@
1
  ---
2
- license: cc-by-nc-sa-4.0
3
  tags:
4
  - generated_from_trainer
 
 
5
  metrics:
6
  - precision
7
  - recall
@@ -9,7 +10,26 @@ metrics:
9
  - accuracy
10
  model-index:
11
  - name: layoutlmv3-finetuned-funsd
12
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +37,13 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # layoutlmv3-finetuned-funsd
19
 
20
- This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5469
23
- - Precision: 0.8633
24
- - Recall: 0.903
25
- - F1: 0.8827
26
- - Accuracy: 0.8435
27
 
28
  ## Model description
29
 
@@ -43,29 +63,33 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 1e-05
46
- - train_batch_size: 10
47
- - eval_batch_size: 10
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - training_steps: 300
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | No log | 1.67 | 25 | 1.2106 | 0.4708 | 0.5275 | 0.4975 | 0.6554 |
58
- | No log | 3.33 | 50 | 0.7854 | 0.7498 | 0.8075 | 0.7776 | 0.7687 |
59
- | No log | 5.0 | 75 | 0.6002 | 0.7932 | 0.8455 | 0.8185 | 0.8142 |
60
- | No log | 6.67 | 100 | 0.6523 | 0.7849 | 0.876 | 0.8280 | 0.7781 |
61
- | No log | 8.33 | 125 | 0.5190 | 0.8152 | 0.8755 | 0.8443 | 0.8354 |
62
- | No log | 10.0 | 150 | 0.5064 | 0.8315 | 0.888 | 0.8588 | 0.8338 |
63
- | No log | 11.67 | 175 | 0.5342 | 0.8482 | 0.8915 | 0.8693 | 0.8344 |
64
- | No log | 13.33 | 200 | 0.5538 | 0.8492 | 0.8925 | 0.8703 | 0.8201 |
65
- | No log | 15.0 | 225 | 0.5336 | 0.8557 | 0.901 | 0.8777 | 0.8349 |
66
- | No log | 16.67 | 250 | 0.5465 | 0.8564 | 0.8975 | 0.8765 | 0.8385 |
67
- | No log | 18.33 | 275 | 0.5403 | 0.8580 | 0.9005 | 0.8788 | 0.8439 |
68
- | No log | 20.0 | 300 | 0.5469 | 0.8633 | 0.903 | 0.8827 | 0.8435 |
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
+ datasets:
5
+ - mp-02/funsd
6
  metrics:
7
  - precision
8
  - recall
 
10
  - accuracy
11
  model-index:
12
  - name: layoutlmv3-finetuned-funsd
13
+ results:
14
+ - task:
15
+ name: Token Classification
16
+ type: token-classification
17
+ dataset:
18
+ name: mp-02/funsd
19
+ type: mp-02/funsd
20
+ metrics:
21
+ - name: Precision
22
+ type: precision
23
+ value: 0.8553875236294896
24
+ - name: Recall
25
+ type: recall
26
+ value: 0.905
27
+ - name: F1
28
+ type: f1
29
+ value: 0.8794946550048591
30
+ - name: Accuracy
31
+ type: accuracy
32
+ value: 0.833371612310519
33
  ---
34
 
35
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
37
 
38
  # layoutlmv3-finetuned-funsd
39
 
40
+ This model is a fine-tuned version of [layoutlmv3](https://huggingface.co/layoutlmv3) on the mp-02/funsd dataset.
41
  It achieves the following results on the evaluation set:
42
+ - Loss: 0.5784
43
+ - Precision: 0.8554
44
+ - Recall: 0.905
45
+ - F1: 0.8795
46
+ - Accuracy: 0.8334
47
 
48
  ## Model description
49
 
 
63
 
64
  The following hyperparameters were used during training:
65
  - learning_rate: 1e-05
66
+ - train_batch_size: 4
67
+ - eval_batch_size: 16
68
  - seed: 42
69
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
70
  - lr_scheduler_type: linear
71
+ - training_steps: 400
72
 
73
  ### Training results
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
76
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
77
+ | No log | 0.66 | 25 | 1.3511 | 0.3301 | 0.3585 | 0.3437 | 0.5721 |
78
+ | No log | 1.32 | 50 | 0.9059 | 0.6965 | 0.7515 | 0.7229 | 0.7615 |
79
+ | No log | 1.97 | 75 | 0.7164 | 0.7613 | 0.831 | 0.7946 | 0.7796 |
80
+ | No log | 2.63 | 100 | 0.6393 | 0.7947 | 0.8575 | 0.8249 | 0.7993 |
81
+ | No log | 3.29 | 125 | 0.5756 | 0.8138 | 0.87 | 0.8410 | 0.8104 |
82
+ | No log | 3.95 | 150 | 0.5508 | 0.8197 | 0.884 | 0.8506 | 0.8323 |
83
+ | No log | 4.61 | 175 | 0.5458 | 0.8325 | 0.8895 | 0.8600 | 0.8328 |
84
+ | No log | 5.26 | 200 | 0.5740 | 0.8234 | 0.8765 | 0.8491 | 0.8266 |
85
+ | No log | 5.92 | 225 | 0.5719 | 0.8532 | 0.8895 | 0.8710 | 0.8361 |
86
+ | No log | 6.58 | 250 | 0.5436 | 0.8439 | 0.9055 | 0.8736 | 0.8264 |
87
+ | No log | 7.24 | 275 | 0.5714 | 0.8520 | 0.9065 | 0.8784 | 0.8290 |
88
+ | No log | 7.89 | 300 | 0.5853 | 0.8560 | 0.9035 | 0.8791 | 0.8281 |
89
+ | No log | 8.55 | 325 | 0.5702 | 0.8578 | 0.905 | 0.8808 | 0.8390 |
90
+ | No log | 9.21 | 350 | 0.5667 | 0.8552 | 0.901 | 0.8775 | 0.8419 |
91
+ | No log | 9.87 | 375 | 0.5793 | 0.8552 | 0.9035 | 0.8787 | 0.8338 |
92
+ | No log | 10.53 | 400 | 0.5784 | 0.8554 | 0.905 | 0.8795 | 0.8334 |
93
 
94
 
95
  ### Framework versions