layoutlmv3-testCUSTOMds20_02
Browse files
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: microsoft/layoutlmv3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: layoutlmv3-testCUSTOMds20_02
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# layoutlmv3-testCUSTOMds20_02
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1298
|
24 |
+
- Precision: 0.8546
|
25 |
+
- Recall: 0.8362
|
26 |
+
- F1: 0.8453
|
27 |
+
- Accuracy: 0.9807
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 1e-05
|
47 |
+
- train_batch_size: 2
|
48 |
+
- eval_batch_size: 2
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- training_steps: 1000
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.25 | 100 | 0.0624 | 0.8578 | 0.8578 | 0.8578 | 0.9837 |
|
59 |
+
| No log | 2.5 | 200 | 0.0858 | 0.8603 | 0.8491 | 0.8547 | 0.9814 |
|
60 |
+
| No log | 3.75 | 300 | 0.0826 | 0.9062 | 0.875 | 0.8904 | 0.9859 |
|
61 |
+
| No log | 5.0 | 400 | 0.0940 | 0.9018 | 0.8707 | 0.8860 | 0.9851 |
|
62 |
+
| 0.0658 | 6.25 | 500 | 0.1237 | 0.8502 | 0.8319 | 0.8410 | 0.9807 |
|
63 |
+
| 0.0658 | 7.5 | 600 | 0.1125 | 0.9045 | 0.8578 | 0.8805 | 0.9844 |
|
64 |
+
| 0.0658 | 8.75 | 700 | 0.1252 | 0.8448 | 0.8448 | 0.8448 | 0.9799 |
|
65 |
+
| 0.0658 | 10.0 | 800 | 0.1156 | 0.8678 | 0.8491 | 0.8584 | 0.9829 |
|
66 |
+
| 0.0658 | 11.25 | 900 | 0.1238 | 0.8559 | 0.8448 | 0.8503 | 0.9822 |
|
67 |
+
| 0.0036 | 12.5 | 1000 | 0.1298 | 0.8546 | 0.8362 | 0.8453 | 0.9807 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.35.2
|
73 |
+
- Pytorch 2.1.0+cu121
|
74 |
+
- Datasets 2.17.1
|
75 |
+
- Tokenizers 0.15.2
|