Hugging Face's logo

Augusto777
/
swiftformer-xs-ve-U13-b-80e

Image Classification
Transformers
TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
199ec9a
•
1 Parent(s): 32b1af5

Model save

Browse files
Files changed (2) hide show
  1. README.md +150 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: MBZUAI/swiftformer-xs
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swiftformer-xs-ve-U13-b-80e
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: validation
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.7391304347826086
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # swiftformer-xs-ve-U13-b-80e
31
+
32
+ This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.7971
35
+ - Accuracy: 0.7391
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0003
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.15
63
+ - num_epochs: 80
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.92 | 6 | 1.3859 | 0.2391 |
70
+ | 1.3857 | 2.0 | 13 | 1.3834 | 0.3261 |
71
+ | 1.3857 | 2.92 | 19 | 1.3789 | 0.1957 |
72
+ | 1.3767 | 4.0 | 26 | 1.3666 | 0.1739 |
73
+ | 1.3227 | 4.92 | 32 | 1.3565 | 0.1522 |
74
+ | 1.3227 | 6.0 | 39 | 1.3887 | 0.1087 |
75
+ | 1.1987 | 6.92 | 45 | 1.3719 | 0.2174 |
76
+ | 1.1071 | 8.0 | 52 | 1.3271 | 0.3043 |
77
+ | 1.1071 | 8.92 | 58 | 1.3562 | 0.2609 |
78
+ | 0.9926 | 10.0 | 65 | 1.2306 | 0.4130 |
79
+ | 0.8721 | 10.92 | 71 | 1.1953 | 0.4565 |
80
+ | 0.8721 | 12.0 | 78 | 1.0754 | 0.5652 |
81
+ | 0.7746 | 12.92 | 84 | 0.9931 | 0.6739 |
82
+ | 0.6859 | 14.0 | 91 | 0.9979 | 0.6739 |
83
+ | 0.6859 | 14.92 | 97 | 0.8964 | 0.6957 |
84
+ | 0.5777 | 16.0 | 104 | 0.9186 | 0.6522 |
85
+ | 0.5136 | 16.92 | 110 | 0.7950 | 0.7609 |
86
+ | 0.5136 | 18.0 | 117 | 0.7794 | 0.7391 |
87
+ | 0.5019 | 18.92 | 123 | 0.8645 | 0.7174 |
88
+ | 0.3879 | 20.0 | 130 | 0.8773 | 0.6957 |
89
+ | 0.3879 | 20.92 | 136 | 0.7304 | 0.7609 |
90
+ | 0.3532 | 22.0 | 143 | 0.6918 | 0.7609 |
91
+ | 0.3532 | 22.92 | 149 | 0.7882 | 0.7609 |
92
+ | 0.3288 | 24.0 | 156 | 0.7132 | 0.7609 |
93
+ | 0.2573 | 24.92 | 162 | 0.6645 | 0.8043 |
94
+ | 0.2573 | 26.0 | 169 | 0.6618 | 0.8478 |
95
+ | 0.239 | 26.92 | 175 | 0.6780 | 0.8043 |
96
+ | 0.2018 | 28.0 | 182 | 0.8138 | 0.6957 |
97
+ | 0.2018 | 28.92 | 188 | 0.8797 | 0.6957 |
98
+ | 0.1961 | 30.0 | 195 | 0.8602 | 0.7174 |
99
+ | 0.214 | 30.92 | 201 | 0.8188 | 0.7391 |
100
+ | 0.214 | 32.0 | 208 | 0.6956 | 0.7609 |
101
+ | 0.1596 | 32.92 | 214 | 0.7981 | 0.7391 |
102
+ | 0.172 | 34.0 | 221 | 0.6845 | 0.7609 |
103
+ | 0.172 | 34.92 | 227 | 0.9340 | 0.7174 |
104
+ | 0.1852 | 36.0 | 234 | 0.9548 | 0.6522 |
105
+ | 0.1492 | 36.92 | 240 | 0.7747 | 0.7609 |
106
+ | 0.1492 | 38.0 | 247 | 0.9907 | 0.6304 |
107
+ | 0.1735 | 38.92 | 253 | 0.8040 | 0.7174 |
108
+ | 0.1405 | 40.0 | 260 | 0.6946 | 0.7609 |
109
+ | 0.1405 | 40.92 | 266 | 0.7019 | 0.7609 |
110
+ | 0.1269 | 42.0 | 273 | 0.8246 | 0.7174 |
111
+ | 0.1269 | 42.92 | 279 | 0.9238 | 0.6739 |
112
+ | 0.1237 | 44.0 | 286 | 0.9354 | 0.6957 |
113
+ | 0.1201 | 44.92 | 292 | 0.7543 | 0.7391 |
114
+ | 0.1201 | 46.0 | 299 | 0.7151 | 0.7174 |
115
+ | 0.1134 | 46.92 | 305 | 0.7284 | 0.7174 |
116
+ | 0.1141 | 48.0 | 312 | 0.7791 | 0.7609 |
117
+ | 0.1141 | 48.92 | 318 | 0.7824 | 0.7391 |
118
+ | 0.1253 | 50.0 | 325 | 0.7319 | 0.7609 |
119
+ | 0.0968 | 50.92 | 331 | 0.7151 | 0.7609 |
120
+ | 0.0968 | 52.0 | 338 | 0.7662 | 0.7609 |
121
+ | 0.0996 | 52.92 | 344 | 0.8086 | 0.7826 |
122
+ | 0.0844 | 54.0 | 351 | 0.8921 | 0.7609 |
123
+ | 0.0844 | 54.92 | 357 | 0.8782 | 0.7609 |
124
+ | 0.1141 | 56.0 | 364 | 0.7864 | 0.7391 |
125
+ | 0.1263 | 56.92 | 370 | 0.7125 | 0.7609 |
126
+ | 0.1263 | 58.0 | 377 | 0.6758 | 0.7609 |
127
+ | 0.0966 | 58.92 | 383 | 0.7243 | 0.7609 |
128
+ | 0.0771 | 60.0 | 390 | 0.7090 | 0.7609 |
129
+ | 0.0771 | 60.92 | 396 | 0.7157 | 0.7609 |
130
+ | 0.0497 | 62.0 | 403 | 0.7549 | 0.7609 |
131
+ | 0.0497 | 62.92 | 409 | 0.7806 | 0.7609 |
132
+ | 0.0848 | 64.0 | 416 | 0.7902 | 0.7391 |
133
+ | 0.0477 | 64.92 | 422 | 0.7684 | 0.7391 |
134
+ | 0.0477 | 66.0 | 429 | 0.8038 | 0.6957 |
135
+ | 0.0823 | 66.92 | 435 | 0.7503 | 0.6957 |
136
+ | 0.0726 | 68.0 | 442 | 0.7634 | 0.7609 |
137
+ | 0.0726 | 68.92 | 448 | 0.7860 | 0.7826 |
138
+ | 0.0799 | 70.0 | 455 | 0.7630 | 0.7609 |
139
+ | 0.067 | 70.92 | 461 | 0.8094 | 0.7391 |
140
+ | 0.067 | 72.0 | 468 | 0.7511 | 0.7391 |
141
+ | 0.0893 | 72.92 | 474 | 0.7738 | 0.7391 |
142
+ | 0.0738 | 73.85 | 480 | 0.7971 | 0.7391 |
143
+
144
+
145
+ ### Framework versions
146
+
147
+ - Transformers 4.36.2
148
+ - Pytorch 2.1.2+cu118
149
+ - Datasets 2.16.1
150
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53931742116097282ab4f3da77c7b2f593596a6f5c964b51c1edf5aa2dbc705b
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed9c63571a0138b9a06455b1dd068ea1fd3c6de14f40740260d4ef1d52eff8a
3
  size 12203648