Hugging Face's logo

Augusto777
/
SW2-DMAE-2

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
b5ed72a
·
verified ·
1 Parent(s): def4e1e

Model save

Browse files
Files changed (3) hide show
  1. README.md +145 -0
  2. model.safetensors +1 -1
  3. runs/Dec03_17-59-04_DESKTOP-SKBE9FB/events.out.tfevents.1733270346.DESKTOP-SKBE9FB.17260.0 +2 -2
README.md ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: SW2-DMAE-2
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.6521739130434783
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # SW2-DMAE-2
32
+
33
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.9880
36
+ - Accuracy: 0.6522
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 1.5e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - num_epochs: 80
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.86 | 3 | 1.6269 | 0.1087 |
70
+ | No log | 2.0 | 7 | 1.6078 | 0.1087 |
71
+ | 1.618 | 2.86 | 10 | 1.5852 | 0.1087 |
72
+ | 1.618 | 4.0 | 14 | 1.5398 | 0.1087 |
73
+ | 1.618 | 4.86 | 17 | 1.4948 | 0.1087 |
74
+ | 1.5162 | 6.0 | 21 | 1.4344 | 0.1087 |
75
+ | 1.5162 | 6.86 | 24 | 1.3879 | 0.1087 |
76
+ | 1.5162 | 8.0 | 28 | 1.3288 | 0.1739 |
77
+ | 1.3459 | 8.86 | 31 | 1.2926 | 0.4565 |
78
+ | 1.3459 | 10.0 | 35 | 1.2562 | 0.4565 |
79
+ | 1.3459 | 10.86 | 38 | 1.2384 | 0.4565 |
80
+ | 1.2384 | 12.0 | 42 | 1.2205 | 0.4565 |
81
+ | 1.2384 | 12.86 | 45 | 1.2174 | 0.4565 |
82
+ | 1.2384 | 14.0 | 49 | 1.2131 | 0.4565 |
83
+ | 1.2049 | 14.86 | 52 | 1.2104 | 0.4565 |
84
+ | 1.2049 | 16.0 | 56 | 1.2086 | 0.4565 |
85
+ | 1.2049 | 16.86 | 59 | 1.2076 | 0.4565 |
86
+ | 1.1815 | 18.0 | 63 | 1.2052 | 0.4565 |
87
+ | 1.1815 | 18.86 | 66 | 1.2049 | 0.4565 |
88
+ | 1.1826 | 20.0 | 70 | 1.2019 | 0.4565 |
89
+ | 1.1826 | 20.86 | 73 | 1.1960 | 0.4565 |
90
+ | 1.1826 | 22.0 | 77 | 1.1927 | 0.4565 |
91
+ | 1.1647 | 22.86 | 80 | 1.1928 | 0.4565 |
92
+ | 1.1647 | 24.0 | 84 | 1.1924 | 0.4565 |
93
+ | 1.1647 | 24.86 | 87 | 1.1903 | 0.4565 |
94
+ | 1.1568 | 26.0 | 91 | 1.1879 | 0.4565 |
95
+ | 1.1568 | 26.86 | 94 | 1.1913 | 0.4565 |
96
+ | 1.1568 | 28.0 | 98 | 1.2046 | 0.4783 |
97
+ | 1.1432 | 28.86 | 101 | 1.1934 | 0.4783 |
98
+ | 1.1432 | 30.0 | 105 | 1.1665 | 0.4783 |
99
+ | 1.1432 | 30.86 | 108 | 1.1601 | 0.4783 |
100
+ | 1.1112 | 32.0 | 112 | 1.1624 | 0.5 |
101
+ | 1.1112 | 32.86 | 115 | 1.1664 | 0.5217 |
102
+ | 1.1112 | 34.0 | 119 | 1.1692 | 0.5 |
103
+ | 1.1132 | 34.86 | 122 | 1.1513 | 0.5435 |
104
+ | 1.1132 | 36.0 | 126 | 1.1384 | 0.5870 |
105
+ | 1.1132 | 36.86 | 129 | 1.1274 | 0.6087 |
106
+ | 1.0642 | 38.0 | 133 | 1.1443 | 0.5870 |
107
+ | 1.0642 | 38.86 | 136 | 1.1651 | 0.5 |
108
+ | 1.0439 | 40.0 | 140 | 1.1493 | 0.5 |
109
+ | 1.0439 | 40.86 | 143 | 1.1331 | 0.5217 |
110
+ | 1.0439 | 42.0 | 147 | 1.1032 | 0.5870 |
111
+ | 1.0362 | 42.86 | 150 | 1.0988 | 0.6304 |
112
+ | 1.0362 | 44.0 | 154 | 1.1093 | 0.5870 |
113
+ | 1.0362 | 44.86 | 157 | 1.1101 | 0.5870 |
114
+ | 1.0177 | 46.0 | 161 | 1.0903 | 0.6304 |
115
+ | 1.0177 | 46.86 | 164 | 1.0691 | 0.6522 |
116
+ | 1.0177 | 48.0 | 168 | 1.0510 | 0.6739 |
117
+ | 1.0 | 48.86 | 171 | 1.0451 | 0.6522 |
118
+ | 1.0 | 50.0 | 175 | 1.0425 | 0.6522 |
119
+ | 1.0 | 50.86 | 178 | 1.0512 | 0.6087 |
120
+ | 0.9636 | 52.0 | 182 | 1.0441 | 0.6304 |
121
+ | 0.9636 | 52.86 | 185 | 1.0402 | 0.6522 |
122
+ | 0.9636 | 54.0 | 189 | 1.0161 | 0.6522 |
123
+ | 0.9744 | 54.86 | 192 | 1.0073 | 0.6522 |
124
+ | 0.9744 | 56.0 | 196 | 1.0048 | 0.6522 |
125
+ | 0.9744 | 56.86 | 199 | 0.9993 | 0.6522 |
126
+ | 0.9233 | 58.0 | 203 | 0.9939 | 0.6522 |
127
+ | 0.9233 | 58.86 | 206 | 0.9939 | 0.6522 |
128
+ | 0.9452 | 60.0 | 210 | 0.9975 | 0.6522 |
129
+ | 0.9452 | 60.86 | 213 | 0.9981 | 0.6087 |
130
+ | 0.9452 | 62.0 | 217 | 0.9985 | 0.6087 |
131
+ | 0.9183 | 62.86 | 220 | 0.9969 | 0.6087 |
132
+ | 0.9183 | 64.0 | 224 | 0.9958 | 0.6304 |
133
+ | 0.9183 | 64.86 | 227 | 0.9928 | 0.6087 |
134
+ | 0.9449 | 66.0 | 231 | 0.9906 | 0.6087 |
135
+ | 0.9449 | 66.86 | 234 | 0.9893 | 0.6304 |
136
+ | 0.9449 | 68.0 | 238 | 0.9881 | 0.6522 |
137
+ | 0.9154 | 68.57 | 240 | 0.9880 | 0.6522 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - Transformers 4.36.2
143
+ - Pytorch 2.1.2+cu118
144
+ - Datasets 2.16.1
145
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d4626de1811acaaf6cb4e7ebf4eeafe6d9d729c1f82ac595632c9f808cffff7
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825eac14515ebf33aff479eafeba2df9f05dad1b869aef3af2603c209fae81f2
3
  size 110356296
runs/Dec03_17-59-04_DESKTOP-SKBE9FB/events.out.tfevents.1733270346.DESKTOP-SKBE9FB.17260.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:083ece48bbb3d661af8d48a664c882c5c3b9022620aaca90071c46c020f9f55d
3
- size 28590
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15d0312d674c8496fc19a722624f461170454aa2c5067f7ee473e4bcce6ec8a
3
+ size 30873