Nguyen Tien
commited on
Commit
•
e47ed66
1
Parent(s):
ddd6cca
Model save
Browse files- README.md +118 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: Visual-Attention-Network/van-tiny
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- recall
|
11 |
+
- precision
|
12 |
+
model-index:
|
13 |
+
- name: teacher-status-van-tiny-256-0
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Image Classification
|
17 |
+
type: image-classification
|
18 |
+
dataset:
|
19 |
+
name: imagefolder
|
20 |
+
type: imagefolder
|
21 |
+
config: default
|
22 |
+
split: train
|
23 |
+
args: default
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.9777777777777777
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.9893162393162394
|
31 |
+
- name: Precision
|
32 |
+
type: precision
|
33 |
+
value: 0.9788583509513742
|
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 |
+
# teacher-status-van-tiny-256-0
|
40 |
+
|
41 |
+
This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on the imagefolder dataset.
|
42 |
+
It achieves the following results on the evaluation set:
|
43 |
+
- Loss: 0.0672
|
44 |
+
- Accuracy: 0.9778
|
45 |
+
- F1 Score: 0.9841
|
46 |
+
- Recall: 0.9893
|
47 |
+
- Precision: 0.9789
|
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: 5e-05
|
67 |
+
- train_batch_size: 32
|
68 |
+
- eval_batch_size: 32
|
69 |
+
- seed: 42
|
70 |
+
- gradient_accumulation_steps: 4
|
71 |
+
- total_train_batch_size: 128
|
72 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
73 |
+
- lr_scheduler_type: linear
|
74 |
+
- lr_scheduler_warmup_ratio: 0.1
|
75 |
+
- num_epochs: 30
|
76 |
+
|
77 |
+
### Training results
|
78 |
+
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Recall | Precision |
|
80 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:------:|:---------:|
|
81 |
+
| 0.6788 | 0.99 | 47 | 0.6437 | 0.6933 | 0.8189 | 1.0 | 0.6933 |
|
82 |
+
| 0.463 | 2.0 | 95 | 0.3406 | 0.8756 | 0.9162 | 0.9808 | 0.8596 |
|
83 |
+
| 0.3596 | 2.99 | 142 | 0.2072 | 0.9304 | 0.9504 | 0.9615 | 0.9395 |
|
84 |
+
| 0.3505 | 4.0 | 190 | 0.1564 | 0.9526 | 0.9661 | 0.9744 | 0.9580 |
|
85 |
+
| 0.2962 | 4.99 | 237 | 0.1262 | 0.9556 | 0.9681 | 0.9722 | 0.9640 |
|
86 |
+
| 0.2762 | 6.0 | 285 | 0.1038 | 0.9644 | 0.9745 | 0.9808 | 0.9684 |
|
87 |
+
| 0.2604 | 6.99 | 332 | 0.0932 | 0.9719 | 0.9798 | 0.9829 | 0.9766 |
|
88 |
+
| 0.2427 | 8.0 | 380 | 0.0928 | 0.9719 | 0.9797 | 0.9786 | 0.9807 |
|
89 |
+
| 0.2465 | 8.99 | 427 | 0.0898 | 0.9719 | 0.9797 | 0.9786 | 0.9807 |
|
90 |
+
| 0.2519 | 10.0 | 475 | 0.0913 | 0.9689 | 0.9775 | 0.9765 | 0.9786 |
|
91 |
+
| 0.2258 | 10.99 | 522 | 0.0847 | 0.9733 | 0.9809 | 0.9872 | 0.9747 |
|
92 |
+
| 0.2184 | 12.0 | 570 | 0.0812 | 0.9793 | 0.9851 | 0.9893 | 0.9809 |
|
93 |
+
| 0.2208 | 12.99 | 617 | 0.0693 | 0.9807 | 0.9861 | 0.9872 | 0.9851 |
|
94 |
+
| 0.2201 | 14.0 | 665 | 0.0628 | 0.9763 | 0.9829 | 0.9850 | 0.9809 |
|
95 |
+
| 0.2251 | 14.99 | 712 | 0.0811 | 0.9733 | 0.9810 | 0.9915 | 0.9707 |
|
96 |
+
| 0.2135 | 16.0 | 760 | 0.0718 | 0.9763 | 0.9829 | 0.9850 | 0.9809 |
|
97 |
+
| 0.1851 | 16.99 | 807 | 0.0791 | 0.9763 | 0.9830 | 0.9872 | 0.9788 |
|
98 |
+
| 0.2152 | 18.0 | 855 | 0.0737 | 0.9748 | 0.9818 | 0.9808 | 0.9829 |
|
99 |
+
| 0.1871 | 18.99 | 902 | 0.0814 | 0.9763 | 0.9830 | 0.9872 | 0.9788 |
|
100 |
+
| 0.1714 | 20.0 | 950 | 0.0692 | 0.9763 | 0.9830 | 0.9893 | 0.9768 |
|
101 |
+
| 0.188 | 20.99 | 997 | 0.0641 | 0.9778 | 0.9840 | 0.9850 | 0.9829 |
|
102 |
+
| 0.191 | 22.0 | 1045 | 0.0644 | 0.9793 | 0.9851 | 0.9872 | 0.9830 |
|
103 |
+
| 0.2025 | 22.99 | 1092 | 0.0675 | 0.9793 | 0.9850 | 0.9829 | 0.9871 |
|
104 |
+
| 0.1753 | 24.0 | 1140 | 0.0655 | 0.9822 | 0.9872 | 0.9893 | 0.9851 |
|
105 |
+
| 0.1857 | 24.99 | 1187 | 0.0731 | 0.9793 | 0.9851 | 0.9915 | 0.9789 |
|
106 |
+
| 0.2007 | 26.0 | 1235 | 0.0677 | 0.9793 | 0.9851 | 0.9915 | 0.9789 |
|
107 |
+
| 0.2086 | 26.99 | 1282 | 0.0640 | 0.9793 | 0.9851 | 0.9893 | 0.9809 |
|
108 |
+
| 0.1666 | 28.0 | 1330 | 0.0712 | 0.9778 | 0.9841 | 0.9893 | 0.9789 |
|
109 |
+
| 0.157 | 28.99 | 1377 | 0.0661 | 0.9807 | 0.9862 | 0.9893 | 0.9830 |
|
110 |
+
| 0.1758 | 29.68 | 1410 | 0.0672 | 0.9778 | 0.9841 | 0.9893 | 0.9789 |
|
111 |
+
|
112 |
+
|
113 |
+
### Framework versions
|
114 |
+
|
115 |
+
- Transformers 4.36.2
|
116 |
+
- Pytorch 2.1.0+cu121
|
117 |
+
- Datasets 2.16.0
|
118 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15480696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98c353494bc53f04d02131daf8d9a3f2d5b30786628fa1882f8dbb024e2d07fb
|
3 |
size 15480696
|