Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV61

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Model card Files
xet
 Metrics Community
RobertoSonic commited on
Commit
9f754f3
·
verified ·
1 Parent(s): deda39a

Model save

Browse files
Files changed (3) hide show
  1. README.md +105 -0
  2. model.safetensors +1 -1
  3. runs/Mar17_01-34-38_5314f4969c12/events.out.tfevents.1742175296.5314f4969c12.2306.0 +2 -2
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-DAV61
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-DAV61
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: 0.3428
22
+ - Accuracy: 0.8857
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: 45
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
+ | 1.1254 | 1.0 | 10 | 1.0551 | 0.48 |
58
+ | 0.967 | 2.0 | 20 | 0.9770 | 0.4571 |
59
+ | 0.8537 | 3.0 | 30 | 0.7128 | 0.7086 |
60
+ | 0.6489 | 4.0 | 40 | 0.5167 | 0.7371 |
61
+ | 0.567 | 5.0 | 50 | 0.3952 | 0.8 |
62
+ | 0.4724 | 6.0 | 60 | 0.3705 | 0.8571 |
63
+ | 0.4106 | 7.0 | 70 | 0.3076 | 0.8743 |
64
+ | 0.3853 | 8.0 | 80 | 0.3155 | 0.8914 |
65
+ | 0.3369 | 9.0 | 90 | 0.2908 | 0.8514 |
66
+ | 0.3345 | 10.0 | 100 | 0.3034 | 0.8457 |
67
+ | 0.3092 | 11.0 | 110 | 0.2575 | 0.88 |
68
+ | 0.3027 | 12.0 | 120 | 0.2486 | 0.8971 |
69
+ | 0.2945 | 13.0 | 130 | 0.2956 | 0.8629 |
70
+ | 0.254 | 14.0 | 140 | 0.2787 | 0.8971 |
71
+ | 0.2476 | 15.0 | 150 | 0.2594 | 0.9029 |
72
+ | 0.2058 | 16.0 | 160 | 0.3091 | 0.8971 |
73
+ | 0.2254 | 17.0 | 170 | 0.2778 | 0.8971 |
74
+ | 0.2165 | 18.0 | 180 | 0.3094 | 0.88 |
75
+ | 0.2501 | 19.0 | 190 | 0.2536 | 0.8914 |
76
+ | 0.2016 | 20.0 | 200 | 0.2652 | 0.9029 |
77
+ | 0.1791 | 21.0 | 210 | 0.2449 | 0.9086 |
78
+ | 0.1401 | 22.0 | 220 | 0.3205 | 0.8743 |
79
+ | 0.17 | 23.0 | 230 | 0.3446 | 0.8686 |
80
+ | 0.1665 | 24.0 | 240 | 0.3058 | 0.8743 |
81
+ | 0.1192 | 25.0 | 250 | 0.3537 | 0.8743 |
82
+ | 0.1249 | 26.0 | 260 | 0.2929 | 0.8743 |
83
+ | 0.143 | 27.0 | 270 | 0.3050 | 0.8743 |
84
+ | 0.1809 | 28.0 | 280 | 0.2964 | 0.8914 |
85
+ | 0.135 | 29.0 | 290 | 0.3047 | 0.8743 |
86
+ | 0.1235 | 30.0 | 300 | 0.3011 | 0.8971 |
87
+ | 0.1351 | 31.0 | 310 | 0.3147 | 0.8914 |
88
+ | 0.1124 | 32.0 | 320 | 0.3123 | 0.8857 |
89
+ | 0.1122 | 33.0 | 330 | 0.3289 | 0.8857 |
90
+ | 0.1163 | 34.0 | 340 | 0.3256 | 0.88 |
91
+ | 0.0885 | 35.0 | 350 | 0.3126 | 0.8971 |
92
+ | 0.097 | 36.0 | 360 | 0.3425 | 0.8857 |
93
+ | 0.1036 | 37.0 | 370 | 0.3221 | 0.8857 |
94
+ | 0.1107 | 38.0 | 380 | 0.3598 | 0.8971 |
95
+ | 0.0928 | 39.0 | 390 | 0.3355 | 0.8857 |
96
+ | 0.1104 | 40.0 | 400 | 0.3425 | 0.8857 |
97
+ | 0.1104 | 40.5128 | 405 | 0.3428 | 0.8857 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.48.3
103
+ - Pytorch 2.6.0+cu124
104
+ - Datasets 3.4.0
105
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f329b3c3c5d3fa7a1271d712907732b3f2dc9698622a9f739a23347b74cf80cd
3
  size 110353212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2107e2253a3faf28e4496017042bee5192cde1e2313a6a785bf2e76d38c76221
3
  size 110353212
runs/Mar17_01-34-38_5314f4969c12/events.out.tfevents.1742175296.5314f4969c12.2306.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf27ca4b95432bf0fe7d746d616c8ea98e7901ca91fec60ea084d3654ceeac2a
3
- size 26898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92da3adcf53a38f14a3cf41ec54ef997d198825d1026678e080d555fc6bc018d
3
+ size 27575