Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
swiftformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
fc70422
•
1 Parent(s): 22e7f25

Model save

Browse files
Files changed (3) hide show
  1. README.md +150 -0
  2. model.safetensors +1 -1
  3. runs/Jun12_11-56-51_DESKTOP-SKBE9FB/events.out.tfevents.1718215013.DESKTOP-SKBE9FB.8908.0 +2 -2
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-80
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: 0.782608695652174
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-80
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: 0.6743
35
+ - Accuracy: 0.7826
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: 0.0002
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: 0.1
63
+ - num_epochs: 80
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.92 | 6 | 1.4461 | 0.1087 |
70
+ | 1.3993 | 2.0 | 13 | 1.4435 | 0.1087 |
71
+ | 1.3993 | 2.92 | 19 | 1.4389 | 0.1087 |
72
+ | 1.3849 | 4.0 | 26 | 1.4284 | 0.1087 |
73
+ | 1.3287 | 4.92 | 32 | 1.4223 | 0.1304 |
74
+ | 1.3287 | 6.0 | 39 | 1.4647 | 0.1087 |
75
+ | 1.2128 | 6.92 | 45 | 1.4184 | 0.1739 |
76
+ | 1.122 | 8.0 | 52 | 1.3262 | 0.1957 |
77
+ | 1.122 | 8.92 | 58 | 1.3298 | 0.1957 |
78
+ | 1.0062 | 10.0 | 65 | 1.2035 | 0.3696 |
79
+ | 0.872 | 10.92 | 71 | 1.3667 | 0.3261 |
80
+ | 0.872 | 12.0 | 78 | 1.2013 | 0.4348 |
81
+ | 0.814 | 12.92 | 84 | 0.9996 | 0.6957 |
82
+ | 0.7228 | 14.0 | 91 | 0.9706 | 0.7609 |
83
+ | 0.7228 | 14.92 | 97 | 0.9295 | 0.7391 |
84
+ | 0.6473 | 16.0 | 104 | 0.8988 | 0.7174 |
85
+ | 0.5696 | 16.92 | 110 | 0.9612 | 0.6739 |
86
+ | 0.5696 | 18.0 | 117 | 0.8713 | 0.7609 |
87
+ | 0.5546 | 18.92 | 123 | 0.8050 | 0.7609 |
88
+ | 0.4747 | 20.0 | 130 | 0.7725 | 0.7609 |
89
+ | 0.4747 | 20.92 | 136 | 0.7933 | 0.6957 |
90
+ | 0.4393 | 22.0 | 143 | 0.7665 | 0.6957 |
91
+ | 0.4393 | 22.92 | 149 | 0.7886 | 0.7174 |
92
+ | 0.4077 | 24.0 | 156 | 0.7824 | 0.7391 |
93
+ | 0.3326 | 24.92 | 162 | 0.7021 | 0.7391 |
94
+ | 0.3326 | 26.0 | 169 | 0.6346 | 0.8261 |
95
+ | 0.315 | 26.92 | 175 | 0.6163 | 0.8696 |
96
+ | 0.2729 | 28.0 | 182 | 0.6938 | 0.8043 |
97
+ | 0.2729 | 28.92 | 188 | 0.7417 | 0.8043 |
98
+ | 0.2218 | 30.0 | 195 | 0.6669 | 0.7826 |
99
+ | 0.2499 | 30.92 | 201 | 0.7111 | 0.7174 |
100
+ | 0.2499 | 32.0 | 208 | 0.6730 | 0.7826 |
101
+ | 0.2218 | 32.92 | 214 | 0.6512 | 0.8043 |
102
+ | 0.2037 | 34.0 | 221 | 0.7165 | 0.7391 |
103
+ | 0.2037 | 34.92 | 227 | 0.6300 | 0.8261 |
104
+ | 0.2367 | 36.0 | 234 | 0.7421 | 0.7826 |
105
+ | 0.1835 | 36.92 | 240 | 0.6644 | 0.8043 |
106
+ | 0.1835 | 38.0 | 247 | 0.6251 | 0.8261 |
107
+ | 0.2073 | 38.92 | 253 | 0.6431 | 0.7826 |
108
+ | 0.1643 | 40.0 | 260 | 0.6348 | 0.8043 |
109
+ | 0.1643 | 40.92 | 266 | 0.6192 | 0.8043 |
110
+ | 0.1685 | 42.0 | 273 | 0.6753 | 0.8043 |
111
+ | 0.1685 | 42.92 | 279 | 0.7440 | 0.7826 |
112
+ | 0.1539 | 44.0 | 286 | 0.7505 | 0.8043 |
113
+ | 0.1658 | 44.92 | 292 | 0.6331 | 0.8261 |
114
+ | 0.1658 | 46.0 | 299 | 0.6550 | 0.8043 |
115
+ | 0.1596 | 46.92 | 305 | 0.6824 | 0.8043 |
116
+ | 0.1534 | 48.0 | 312 | 0.6971 | 0.8043 |
117
+ | 0.1534 | 48.92 | 318 | 0.6347 | 0.8261 |
118
+ | 0.1677 | 50.0 | 325 | 0.6392 | 0.8261 |
119
+ | 0.1453 | 50.92 | 331 | 0.6369 | 0.8043 |
120
+ | 0.1453 | 52.0 | 338 | 0.6230 | 0.7826 |
121
+ | 0.1385 | 52.92 | 344 | 0.6432 | 0.7609 |
122
+ | 0.1221 | 54.0 | 351 | 0.6757 | 0.7391 |
123
+ | 0.1221 | 54.92 | 357 | 0.7383 | 0.7609 |
124
+ | 0.1433 | 56.0 | 364 | 0.7100 | 0.7609 |
125
+ | 0.1567 | 56.92 | 370 | 0.6862 | 0.7609 |
126
+ | 0.1567 | 58.0 | 377 | 0.6654 | 0.7609 |
127
+ | 0.1361 | 58.92 | 383 | 0.6665 | 0.7826 |
128
+ | 0.1157 | 60.0 | 390 | 0.6439 | 0.7826 |
129
+ | 0.1157 | 60.92 | 396 | 0.6306 | 0.8261 |
130
+ | 0.0934 | 62.0 | 403 | 0.6546 | 0.8043 |
131
+ | 0.0934 | 62.92 | 409 | 0.6651 | 0.8043 |
132
+ | 0.1123 | 64.0 | 416 | 0.6568 | 0.7609 |
133
+ | 0.0855 | 64.92 | 422 | 0.6507 | 0.7609 |
134
+ | 0.0855 | 66.0 | 429 | 0.6667 | 0.8043 |
135
+ | 0.1135 | 66.92 | 435 | 0.6516 | 0.7826 |
136
+ | 0.0932 | 68.0 | 442 | 0.6596 | 0.8043 |
137
+ | 0.0932 | 68.92 | 448 | 0.6772 | 0.8043 |
138
+ | 0.1228 | 70.0 | 455 | 0.6526 | 0.7609 |
139
+ | 0.0878 | 70.92 | 461 | 0.6731 | 0.8261 |
140
+ | 0.0878 | 72.0 | 468 | 0.6351 | 0.7826 |
141
+ | 0.1073 | 72.92 | 474 | 0.6269 | 0.7826 |
142
+ | 0.1028 | 73.85 | 480 | 0.6743 | 0.7826 |
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 sha256:56f1392000844281a308ce33f8612c786b6290e3a6c47b3e188efc257077d217
3
  size 12203648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7501f41e5c8db06aae5307f125b05d57d785068af386794feb8247db569368b8
3
  size 12203648
runs/Jun12_11-56-51_DESKTOP-SKBE9FB/events.out.tfevents.1718215013.DESKTOP-SKBE9FB.8908.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3349d75b6a2c3e3a0ecb85f6bea94174cb6dd0f4a5275e97a3eda7d0665cf7f
3
- size 35371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad549dc7493fddc39807116e7bef68c3dbe48948a04f5b7e1a1403c514f11b2
3
+ size 36205