nielsr HF staff commited on
Commit
e13cfdd
1 Parent(s): 64b946a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +95 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - cord
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: layoutlmv3-finetuned-cord
13
+ results:
14
+ - task:
15
+ name: Token Classification
16
+ type: token-classification
17
+ dataset:
18
+ name: cord
19
+ type: cord
20
+ args: cord
21
+ metrics:
22
+ - name: Precision
23
+ type: precision
24
+ value: 0.9190581309786607
25
+ - name: Recall
26
+ type: recall
27
+ value: 0.9348802395209581
28
+ - name: F1
29
+ type: f1
30
+ value: 0.9269016697588126
31
+ - name: Accuracy
32
+ type: accuracy
33
+ value: 0.9384550084889643
34
+ ---
35
+
36
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
37
+ should probably proofread and complete it, then remove this comment. -->
38
+
39
+ # layoutlmv3-finetuned-cord
40
+
41
+ This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord dataset.
42
+ It achieves the following results on the evaluation set:
43
+ - Loss: 0.3056
44
+ - Precision: 0.9191
45
+ - Recall: 0.9349
46
+ - F1: 0.9269
47
+ - Accuracy: 0.9385
48
+
49
+ ## Model description
50
+
51
+ More information needed
52
+
53
+ ## Intended uses & limitations
54
+
55
+ More information needed
56
+
57
+ ## Training and evaluation data
58
+
59
+ More information needed
60
+
61
+ ## Training procedure
62
+
63
+ ### Training hyperparameters
64
+
65
+ The following hyperparameters were used during training:
66
+ - learning_rate: 1e-05
67
+ - train_batch_size: 16
68
+ - eval_batch_size: 16
69
+ - seed: 42
70
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
71
+ - lr_scheduler_type: linear
72
+ - training_steps: 1000
73
+
74
+ ### Training results
75
+
76
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
77
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
78
+ | No log | 2.0 | 100 | 1.6054 | 0.52 | 0.6130 | 0.5627 | 0.6367 |
79
+ | No log | 4.0 | 200 | 0.9172 | 0.7923 | 0.8278 | 0.8097 | 0.8315 |
80
+ | No log | 6.0 | 300 | 0.6382 | 0.8367 | 0.8630 | 0.8497 | 0.8667 |
81
+ | No log | 8.0 | 400 | 0.4974 | 0.8648 | 0.8907 | 0.8776 | 0.8960 |
82
+ | 1.1589 | 10.0 | 500 | 0.4124 | 0.8769 | 0.9064 | 0.8914 | 0.9164 |
83
+ | 1.1589 | 12.0 | 600 | 0.3767 | 0.8961 | 0.9169 | 0.9064 | 0.9236 |
84
+ | 1.1589 | 14.0 | 700 | 0.3388 | 0.9120 | 0.9304 | 0.9211 | 0.9338 |
85
+ | 1.1589 | 16.0 | 800 | 0.3138 | 0.9198 | 0.9356 | 0.9276 | 0.9393 |
86
+ | 1.1589 | 18.0 | 900 | 0.3073 | 0.9176 | 0.9334 | 0.9254 | 0.9376 |
87
+ | 0.2992 | 20.0 | 1000 | 0.3056 | 0.9191 | 0.9349 | 0.9269 | 0.9385 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.19.0.dev0
93
+ - Pytorch 1.11.0+cu113
94
+ - Datasets 2.0.0
95
+ - Tokenizers 0.11.6