Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV72

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Model card Files
xet
Metrics Community
RobertoSonic commited on
Commit
845457a
·
verified ·
1 Parent(s): d713d9b

Model save

Browse files
Files changed (3) hide show
  1. README.md +158 -0
  2. model.safetensors +1 -1
  3. runs/May24_05-36-02_926d23d08976/events.out.tfevents.1748064992.926d23d08976.4296.0 +2 -2
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swinv2-tiny-patch4-window8-256-dmae-humeda-DAV72
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # swinv2-tiny-patch4-window8-256-dmae-humeda-DAV72
18
+
19
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7140
22
+ - Accuracy: 0.8743
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 4e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 64
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 100
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
+ | 1.0851 | 1.0 | 15 | 1.0597 | 0.4857 |
58
+ | 0.9595 | 2.0 | 30 | 0.9427 | 0.64 |
59
+ | 0.8642 | 3.0 | 45 | 0.6913 | 0.7086 |
60
+ | 0.5836 | 4.0 | 60 | 0.5780 | 0.7257 |
61
+ | 0.5395 | 5.0 | 75 | 0.4822 | 0.7829 |
62
+ | 0.4215 | 6.0 | 90 | 0.4077 | 0.8229 |
63
+ | 0.4329 | 7.0 | 105 | 0.4352 | 0.8114 |
64
+ | 0.3695 | 8.0 | 120 | 0.3244 | 0.8743 |
65
+ | 0.3314 | 9.0 | 135 | 0.3186 | 0.8914 |
66
+ | 0.3176 | 10.0 | 150 | 0.3788 | 0.8514 |
67
+ | 0.3368 | 11.0 | 165 | 0.3458 | 0.8629 |
68
+ | 0.2558 | 12.0 | 180 | 0.4196 | 0.8457 |
69
+ | 0.2579 | 13.0 | 195 | 0.3485 | 0.8743 |
70
+ | 0.2413 | 14.0 | 210 | 0.4509 | 0.8629 |
71
+ | 0.2374 | 15.0 | 225 | 0.3904 | 0.8743 |
72
+ | 0.2214 | 16.0 | 240 | 0.3461 | 0.8514 |
73
+ | 0.2189 | 17.0 | 255 | 0.5986 | 0.8229 |
74
+ | 0.2458 | 18.0 | 270 | 0.3360 | 0.8914 |
75
+ | 0.2431 | 19.0 | 285 | 0.3475 | 0.8857 |
76
+ | 0.2136 | 20.0 | 300 | 0.3242 | 0.88 |
77
+ | 0.1871 | 21.0 | 315 | 0.4103 | 0.8857 |
78
+ | 0.1996 | 22.0 | 330 | 0.3606 | 0.9029 |
79
+ | 0.1367 | 23.0 | 345 | 0.4657 | 0.8629 |
80
+ | 0.1963 | 24.0 | 360 | 0.4267 | 0.8743 |
81
+ | 0.1519 | 25.0 | 375 | 0.4322 | 0.8686 |
82
+ | 0.1365 | 26.0 | 390 | 0.4214 | 0.88 |
83
+ | 0.1158 | 27.0 | 405 | 0.4472 | 0.8743 |
84
+ | 0.1621 | 28.0 | 420 | 0.4020 | 0.8743 |
85
+ | 0.1271 | 29.0 | 435 | 0.4054 | 0.8857 |
86
+ | 0.136 | 30.0 | 450 | 0.4286 | 0.9143 |
87
+ | 0.1386 | 31.0 | 465 | 0.5015 | 0.8857 |
88
+ | 0.1153 | 32.0 | 480 | 0.6675 | 0.8629 |
89
+ | 0.1139 | 33.0 | 495 | 0.5458 | 0.8971 |
90
+ | 0.144 | 34.0 | 510 | 0.5303 | 0.88 |
91
+ | 0.1542 | 35.0 | 525 | 0.5164 | 0.8914 |
92
+ | 0.1208 | 36.0 | 540 | 0.5690 | 0.88 |
93
+ | 0.1034 | 37.0 | 555 | 0.7427 | 0.8571 |
94
+ | 0.0889 | 38.0 | 570 | 0.9084 | 0.8286 |
95
+ | 0.1355 | 39.0 | 585 | 0.5977 | 0.8743 |
96
+ | 0.0895 | 40.0 | 600 | 0.5400 | 0.8914 |
97
+ | 0.1072 | 41.0 | 615 | 0.6018 | 0.8743 |
98
+ | 0.1356 | 42.0 | 630 | 0.5493 | 0.8743 |
99
+ | 0.0953 | 43.0 | 645 | 0.5350 | 0.8914 |
100
+ | 0.0781 | 44.0 | 660 | 0.5269 | 0.88 |
101
+ | 0.0854 | 45.0 | 675 | 0.5428 | 0.88 |
102
+ | 0.0983 | 46.0 | 690 | 0.4897 | 0.8857 |
103
+ | 0.0944 | 47.0 | 705 | 0.5177 | 0.8971 |
104
+ | 0.1152 | 48.0 | 720 | 0.6401 | 0.8629 |
105
+ | 0.0608 | 49.0 | 735 | 0.7380 | 0.8629 |
106
+ | 0.0898 | 50.0 | 750 | 0.4922 | 0.8971 |
107
+ | 0.0923 | 51.0 | 765 | 0.5427 | 0.8971 |
108
+ | 0.0743 | 52.0 | 780 | 0.9941 | 0.84 |
109
+ | 0.0753 | 53.0 | 795 | 0.5342 | 0.8857 |
110
+ | 0.0751 | 54.0 | 810 | 0.6452 | 0.88 |
111
+ | 0.1222 | 55.0 | 825 | 0.6297 | 0.8743 |
112
+ | 0.0786 | 56.0 | 840 | 0.6592 | 0.8629 |
113
+ | 0.134 | 57.0 | 855 | 0.6541 | 0.8686 |
114
+ | 0.092 | 58.0 | 870 | 0.6523 | 0.8571 |
115
+ | 0.1036 | 59.0 | 885 | 0.5562 | 0.8971 |
116
+ | 0.0825 | 60.0 | 900 | 0.6117 | 0.8743 |
117
+ | 0.0923 | 61.0 | 915 | 0.5778 | 0.8686 |
118
+ | 0.0909 | 62.0 | 930 | 0.5974 | 0.8686 |
119
+ | 0.0536 | 63.0 | 945 | 0.7557 | 0.8514 |
120
+ | 0.0572 | 64.0 | 960 | 0.6255 | 0.8857 |
121
+ | 0.0824 | 65.0 | 975 | 0.6768 | 0.8686 |
122
+ | 0.0773 | 66.0 | 990 | 0.5942 | 0.9029 |
123
+ | 0.0495 | 67.0 | 1005 | 0.7902 | 0.8571 |
124
+ | 0.0649 | 68.0 | 1020 | 0.6097 | 0.8914 |
125
+ | 0.0852 | 69.0 | 1035 | 0.6614 | 0.8914 |
126
+ | 0.0634 | 70.0 | 1050 | 0.6604 | 0.8914 |
127
+ | 0.0774 | 71.0 | 1065 | 0.7848 | 0.8514 |
128
+ | 0.0803 | 72.0 | 1080 | 0.6424 | 0.8914 |
129
+ | 0.0645 | 73.0 | 1095 | 0.7508 | 0.8857 |
130
+ | 0.0483 | 74.0 | 1110 | 0.7523 | 0.8629 |
131
+ | 0.0586 | 75.0 | 1125 | 0.8278 | 0.8629 |
132
+ | 0.1 | 76.0 | 1140 | 0.7503 | 0.8686 |
133
+ | 0.0434 | 77.0 | 1155 | 0.7820 | 0.8743 |
134
+ | 0.0792 | 78.0 | 1170 | 0.7016 | 0.88 |
135
+ | 0.055 | 79.0 | 1185 | 0.8635 | 0.8571 |
136
+ | 0.0666 | 80.0 | 1200 | 0.7208 | 0.8686 |
137
+ | 0.0563 | 81.0 | 1215 | 0.7606 | 0.8686 |
138
+ | 0.0535 | 82.0 | 1230 | 0.7329 | 0.88 |
139
+ | 0.0499 | 83.0 | 1245 | 0.7253 | 0.88 |
140
+ | 0.0418 | 84.0 | 1260 | 0.7429 | 0.8686 |
141
+ | 0.0736 | 85.0 | 1275 | 0.7621 | 0.8743 |
142
+ | 0.0593 | 86.0 | 1290 | 0.7970 | 0.8571 |
143
+ | 0.0658 | 87.0 | 1305 | 0.7211 | 0.8686 |
144
+ | 0.0531 | 88.0 | 1320 | 0.7420 | 0.8686 |
145
+ | 0.0604 | 89.0 | 1335 | 0.7151 | 0.8743 |
146
+ | 0.0661 | 90.0 | 1350 | 0.6881 | 0.8857 |
147
+ | 0.058 | 91.0 | 1365 | 0.7139 | 0.8686 |
148
+ | 0.0436 | 92.0 | 1380 | 0.7260 | 0.8686 |
149
+ | 0.0733 | 93.0 | 1395 | 0.7150 | 0.8743 |
150
+ | 0.0501 | 93.3390 | 1400 | 0.7140 | 0.8743 |
151
+
152
+
153
+ ### Framework versions
154
+
155
+ - Transformers 4.51.3
156
+ - Pytorch 2.6.0+cu124
157
+ - Datasets 2.19.0
158
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a149949c7afc2ccba4e8813320c07f193dbc8d7571b8795ba5299e0b9dff31cd
3
  size 110353212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8096b86b66c456463c656e5cbaa2b47195dfeb6f49634086af03780ec63448f
3
  size 110353212
runs/May24_05-36-02_926d23d08976/events.out.tfevents.1748064992.926d23d08976.4296.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78ff8a69b6b6e887223d7ef6f0585d91785ca0aad2670c4c81c3e861777552c1
3
- size 64797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d794fa773ec9ef1a174396c33d254a48234076862a8485d03f11f86ff17cd47d
3
+ size 65685