Harisudhan commited on
Commit
ab7ef59
1 Parent(s): 338b4bc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.9472118959107807
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.9535928143712575
31
+ - name: F1
32
+ type: f1
33
+ value: 0.9503916449086163
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.9562818336162988
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: 0.2152
47
+ - Precision: 0.9472
48
+ - Recall: 0.9536
49
+ - F1: 0.9504
50
+ - Accuracy: 0.9563
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: 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: 2500
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 1.56 | 250 | 0.9909 | 0.7582 | 0.8099 | 0.7832 | 0.8128 |
82
+ | 1.3653 | 3.12 | 500 | 0.5650 | 0.8392 | 0.8675 | 0.8531 | 0.8756 |
83
+ | 1.3653 | 4.69 | 750 | 0.3851 | 0.8865 | 0.9177 | 0.9018 | 0.9181 |
84
+ | 0.3744 | 6.25 | 1000 | 0.3104 | 0.9280 | 0.9364 | 0.9322 | 0.9380 |
85
+ | 0.3744 | 7.81 | 1250 | 0.2778 | 0.9347 | 0.9424 | 0.9385 | 0.9440 |
86
+ | 0.1955 | 9.38 | 1500 | 0.2316 | 0.9327 | 0.9446 | 0.9386 | 0.9440 |
87
+ | 0.1955 | 10.94 | 1750 | 0.2461 | 0.9414 | 0.9491 | 0.9452 | 0.9533 |
88
+ | 0.1349 | 12.5 | 2000 | 0.2316 | 0.9379 | 0.9491 | 0.9435 | 0.9478 |
89
+ | 0.1349 | 14.06 | 2250 | 0.2227 | 0.9487 | 0.9551 | 0.9519 | 0.9533 |
90
+ | 0.1024 | 15.62 | 2500 | 0.2152 | 0.9472 | 0.9536 | 0.9504 | 0.9563 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.23.1
96
+ - Pytorch 1.12.1+cu113
97
+ - Datasets 2.6.1
98
+ - Tokenizers 0.13.1