Commit
•
035587a
1
Parent(s):
447b816
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- image_folder
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: deit_flyswot
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Image Classification
|
13 |
+
type: image-classification
|
14 |
+
dataset:
|
15 |
+
name: image_folder
|
16 |
+
type: image_folder
|
17 |
+
args: default
|
18 |
+
metrics:
|
19 |
+
- name: F1
|
20 |
+
type: f1
|
21 |
+
value: 0.990761405263678
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# deit_flyswot
|
28 |
+
|
29 |
+
This model was trained from scratch on the image_folder dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 0.0755
|
32 |
+
- F1: 0.9908
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 2e-05
|
52 |
+
- train_batch_size: 32
|
53 |
+
- eval_batch_size: 32
|
54 |
+
- seed: 666
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 30
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
64 |
+
| No log | 1.0 | 52 | 0.5710 | 0.8095 |
|
65 |
+
| No log | 2.0 | 104 | 0.2814 | 0.9380 |
|
66 |
+
| No log | 3.0 | 156 | 0.1719 | 0.9555 |
|
67 |
+
| No log | 4.0 | 208 | 0.1410 | 0.9692 |
|
68 |
+
| No log | 5.0 | 260 | 0.1457 | 0.9680 |
|
69 |
+
| No log | 6.0 | 312 | 0.1084 | 0.9747 |
|
70 |
+
| No log | 7.0 | 364 | 0.0892 | 0.9736 |
|
71 |
+
| No log | 8.0 | 416 | 0.0962 | 0.9831 |
|
72 |
+
| No log | 9.0 | 468 | 0.0819 | 0.9796 |
|
73 |
+
| 0.2034 | 10.0 | 520 | 0.0916 | 0.9778 |
|
74 |
+
| 0.2034 | 11.0 | 572 | 0.0793 | 0.9827 |
|
75 |
+
| 0.2034 | 12.0 | 624 | 0.0818 | 0.9894 |
|
76 |
+
| 0.2034 | 13.0 | 676 | 0.0852 | 0.9807 |
|
77 |
+
| 0.2034 | 14.0 | 728 | 0.0938 | 0.9778 |
|
78 |
+
| 0.2034 | 15.0 | 780 | 0.0814 | 0.9876 |
|
79 |
+
| 0.2034 | 16.0 | 832 | 0.0702 | 0.9892 |
|
80 |
+
| 0.2034 | 17.0 | 884 | 0.0801 | 0.9892 |
|
81 |
+
| 0.2034 | 18.0 | 936 | 0.0806 | 0.9892 |
|
82 |
+
| 0.2034 | 19.0 | 988 | 0.0769 | 0.9926 |
|
83 |
+
| 0.0115 | 20.0 | 1040 | 0.0800 | 0.9926 |
|
84 |
+
| 0.0115 | 21.0 | 1092 | 0.0794 | 0.9926 |
|
85 |
+
| 0.0115 | 22.0 | 1144 | 0.0762 | 0.9846 |
|
86 |
+
| 0.0115 | 23.0 | 1196 | 0.0789 | 0.9830 |
|
87 |
+
| 0.0115 | 24.0 | 1248 | 0.0794 | 0.9829 |
|
88 |
+
| 0.0115 | 25.0 | 1300 | 0.0770 | 0.9908 |
|
89 |
+
| 0.0115 | 26.0 | 1352 | 0.0791 | 0.9829 |
|
90 |
+
| 0.0115 | 27.0 | 1404 | 0.0813 | 0.9892 |
|
91 |
+
| 0.0115 | 28.0 | 1456 | 0.0816 | 0.9908 |
|
92 |
+
| 0.0058 | 29.0 | 1508 | 0.0774 | 0.9908 |
|
93 |
+
| 0.0058 | 30.0 | 1560 | 0.0755 | 0.9908 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.17.0
|
99 |
+
- Pytorch 1.10.0+cu111
|
100 |
+
- Datasets 2.0.0
|
101 |
+
- Tokenizers 0.11.6
|