tiennvcs commited on
Commit
9977165
1 Parent(s): 677ce4a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: layoutlmv2-base-uncased-finetuned-docvqa
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # layoutlmv2-base-uncased-finetuned-docvqa
14
+
15
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.1940
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 250500
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 1.463 | 0.27 | 1000 | 1.6272 |
49
+ | 0.9447 | 0.53 | 2000 | 1.3646 |
50
+ | 0.7725 | 0.8 | 3000 | 1.2560 |
51
+ | 0.5762 | 1.06 | 4000 | 1.3582 |
52
+ | 0.4382 | 1.33 | 5000 | 1.2490 |
53
+ | 0.4515 | 1.59 | 6000 | 1.1860 |
54
+ | 0.383 | 1.86 | 7000 | 1.1940 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.12.2
60
+ - Pytorch 1.8.0+cu101
61
+ - Datasets 1.14.0
62
+ - Tokenizers 0.10.3