Hugging Face's logo

DrishtiSharma
/
LayoutLMv3-Finetuned-CORD_100

Token Classification
Transformers
PyTorch
TensorBoard
layoutlmv3
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
DrishtiSharma commited on
Commit
ee0ec3a
•
1 Parent(s): ebf2400

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - cord-layoutlmv3
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: LayoutLMv3-Finetuned-CORD_100
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: cord-layoutlmv3
20
+ type: cord-layoutlmv3
21
+ config: cord
22
+ split: train
23
+ args: cord
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.9524870081662955
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9603293413173652
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9563920983973164
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9647707979626485
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # LayoutLMv3-Finetuned-CORD_100
43
+
44
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.1948
47
+ - Precision: 0.9525
48
+ - Recall: 0.9603
49
+ - F1: 0.9564
50
+ - Accuracy: 0.9648
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 1.1e-05
70
+ - train_batch_size: 5
71
+ - eval_batch_size: 5
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - training_steps: 3000
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 1.56 | 250 | 0.9568 | 0.7298 | 0.7844 | 0.7561 | 0.7992 |
82
+ | 1.3271 | 3.12 | 500 | 0.5239 | 0.8398 | 0.8713 | 0.8553 | 0.8858 |
83
+ | 1.3271 | 4.69 | 750 | 0.3586 | 0.8945 | 0.9207 | 0.9074 | 0.9300 |
84
+ | 0.3495 | 6.25 | 1000 | 0.2716 | 0.9298 | 0.9416 | 0.9357 | 0.9410 |
85
+ | 0.3495 | 7.81 | 1250 | 0.2331 | 0.9198 | 0.9356 | 0.9276 | 0.9474 |
86
+ | 0.1725 | 9.38 | 1500 | 0.2134 | 0.9379 | 0.9499 | 0.9438 | 0.9529 |
87
+ | 0.1725 | 10.94 | 1750 | 0.2079 | 0.9401 | 0.9513 | 0.9457 | 0.9605 |
88
+ | 0.1116 | 12.5 | 2000 | 0.1992 | 0.9554 | 0.9618 | 0.9586 | 0.9656 |
89
+ | 0.1116 | 14.06 | 2250 | 0.1941 | 0.9517 | 0.9588 | 0.9553 | 0.9631 |
90
+ | 0.0762 | 15.62 | 2500 | 0.1966 | 0.9503 | 0.9588 | 0.9545 | 0.9639 |
91
+ | 0.0762 | 17.19 | 2750 | 0.1951 | 0.9510 | 0.9588 | 0.9549 | 0.9626 |
92
+ | 0.0636 | 18.75 | 3000 | 0.1948 | 0.9525 | 0.9603 | 0.9564 | 0.9648 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.22.1
98
+ - Pytorch 1.12.1+cu113
99
+ - Datasets 2.4.0
100
+ - Tokenizers 0.12.1