Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-ex

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Model card Files Metrics Community
Augusto777 commited on
Commit
70139a9
·
verified ·
1 Parent(s): c3dc3b1

Model save

Browse files
Files changed (3) hide show
  1. README.md +38 -38
  2. model.safetensors +1 -1
  3. runs/Dec02_14-35-31_DESKTOP-SKBE9FB/events.out.tfevents.1733171732.DESKTOP-SKBE9FB.18464.0 +2 -2
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 1.6325
36
  - Accuracy: 0.4565
37
 
38
  ## Model description
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 4e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
@@ -60,48 +60,48 @@ The following hyperparameters were used during training:
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
- - lr_scheduler_warmup_ratio: 0.05
64
  - num_epochs: 40
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.86 | 3 | 7.9360 | 0.1087 |
71
- | No log | 2.0 | 7 | 7.8361 | 0.1087 |
72
- | 7.9038 | 2.86 | 10 | 7.5850 | 0.1087 |
73
- | 7.9038 | 4.0 | 14 | 7.0626 | 0.1087 |
74
- | 7.9038 | 4.86 | 17 | 6.5536 | 0.1087 |
75
- | 6.9398 | 6.0 | 21 | 5.9113 | 0.1087 |
76
- | 6.9398 | 6.86 | 24 | 5.4225 | 0.1087 |
77
- | 6.9398 | 8.0 | 28 | 4.8409 | 0.1087 |
78
- | 5.3358 | 8.86 | 31 | 4.4200 | 0.1087 |
79
- | 5.3358 | 10.0 | 35 | 3.8921 | 0.1087 |
80
- | 5.3358 | 10.86 | 38 | 3.5183 | 0.1087 |
81
- | 4.1182 | 12.0 | 42 | 3.0596 | 0.1087 |
82
- | 4.1182 | 12.86 | 45 | 2.7530 | 0.1087 |
83
- | 4.1182 | 14.0 | 49 | 2.3976 | 0.1087 |
84
- | 2.8935 | 14.86 | 52 | 2.1733 | 0.1087 |
85
- | 2.8935 | 16.0 | 56 | 1.9296 | 0.1087 |
86
- | 2.8935 | 16.86 | 59 | 1.7846 | 0.1087 |
87
- | 2.0579 | 18.0 | 63 | 1.6325 | 0.4565 |
88
- | 2.0579 | 18.86 | 66 | 1.5432 | 0.4565 |
89
- | 1.6272 | 20.0 | 70 | 1.4467 | 0.4565 |
90
- | 1.6272 | 20.86 | 73 | 1.3865 | 0.4565 |
91
- | 1.6272 | 22.0 | 77 | 1.3220 | 0.4565 |
92
- | 1.3699 | 22.86 | 80 | 1.2848 | 0.4565 |
93
- | 1.3699 | 24.0 | 84 | 1.2489 | 0.4565 |
94
- | 1.3699 | 24.86 | 87 | 1.2313 | 0.4565 |
95
- | 1.2469 | 26.0 | 91 | 1.2175 | 0.4565 |
96
- | 1.2469 | 26.86 | 94 | 1.2126 | 0.4565 |
97
- | 1.2469 | 28.0 | 98 | 1.2115 | 0.4565 |
98
- | 1.2128 | 28.86 | 101 | 1.2108 | 0.4565 |
99
- | 1.2128 | 30.0 | 105 | 1.2107 | 0.4565 |
100
- | 1.2128 | 30.86 | 108 | 1.2102 | 0.4565 |
101
- | 1.1889 | 32.0 | 112 | 1.2094 | 0.4565 |
102
- | 1.1889 | 32.86 | 115 | 1.2090 | 0.4565 |
103
- | 1.1889 | 34.0 | 119 | 1.2087 | 0.4565 |
104
- | 1.2137 | 34.29 | 120 | 1.2087 | 0.4565 |
105
 
106
 
107
  ### Framework versions
 
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: 1.2067
36
  - Accuracy: 0.4565
37
 
38
  ## Model description
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
 
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
+ - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 40
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.86 | 3 | 3.4880 | 0.1087 |
71
+ | No log | 2.0 | 7 | 2.8351 | 0.4565 |
72
+ | 9.7554 | 2.86 | 10 | 3.8518 | 0.4565 |
73
+ | 9.7554 | 4.0 | 14 | 2.7398 | 0.1087 |
74
+ | 9.7554 | 4.86 | 17 | 4.4873 | 0.4565 |
75
+ | 3.9513 | 6.0 | 21 | 3.8559 | 0.3261 |
76
+ | 3.9513 | 6.86 | 24 | 2.1413 | 0.4565 |
77
+ | 3.9513 | 8.0 | 28 | 1.4670 | 0.3261 |
78
+ | 2.7557 | 8.86 | 31 | 1.3523 | 0.4565 |
79
+ | 2.7557 | 10.0 | 35 | 1.4153 | 0.3261 |
80
+ | 2.7557 | 10.86 | 38 | 1.3797 | 0.3261 |
81
+ | 1.6168 | 12.0 | 42 | 1.4730 | 0.4565 |
82
+ | 1.6168 | 12.86 | 45 | 1.2620 | 0.3261 |
83
+ | 1.6168 | 14.0 | 49 | 1.2210 | 0.4565 |
84
+ | 1.4447 | 14.86 | 52 | 1.2588 | 0.3261 |
85
+ | 1.4447 | 16.0 | 56 | 1.2459 | 0.4565 |
86
+ | 1.4447 | 16.86 | 59 | 1.2858 | 0.3261 |
87
+ | 1.2597 | 18.0 | 63 | 1.2520 | 0.4565 |
88
+ | 1.2597 | 18.86 | 66 | 1.2308 | 0.4565 |
89
+ | 1.2406 | 20.0 | 70 | 1.2240 | 0.4565 |
90
+ | 1.2406 | 20.86 | 73 | 1.2277 | 0.3261 |
91
+ | 1.2406 | 22.0 | 77 | 1.2437 | 0.4565 |
92
+ | 1.2506 | 22.86 | 80 | 1.2311 | 0.3261 |
93
+ | 1.2506 | 24.0 | 84 | 1.2103 | 0.4565 |
94
+ | 1.2506 | 24.86 | 87 | 1.2072 | 0.4565 |
95
+ | 1.2026 | 26.0 | 91 | 1.2174 | 0.4565 |
96
+ | 1.2026 | 26.86 | 94 | 1.2164 | 0.4565 |
97
+ | 1.2026 | 28.0 | 98 | 1.2149 | 0.4565 |
98
+ | 1.2 | 28.86 | 101 | 1.2062 | 0.4565 |
99
+ | 1.2 | 30.0 | 105 | 1.2066 | 0.4565 |
100
+ | 1.2 | 30.86 | 108 | 1.2087 | 0.4565 |
101
+ | 1.2065 | 32.0 | 112 | 1.2077 | 0.4565 |
102
+ | 1.2065 | 32.86 | 115 | 1.2070 | 0.4565 |
103
+ | 1.2065 | 34.0 | 119 | 1.2067 | 0.4565 |
104
+ | 1.1998 | 34.29 | 120 | 1.2067 | 0.4565 |
105
 
106
 
107
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b79e9a3c7a4a25cff154e5e55f4106719181a07af40711dc7333e46e285eb3ba
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bea64174289b62da313d3e0c85183710e1f6950a856e577e088e1bbf66152b5
3
  size 110356296
runs/Dec02_14-35-31_DESKTOP-SKBE9FB/events.out.tfevents.1733171732.DESKTOP-SKBE9FB.18464.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef080c508110dbaf5913d7b8832c3b7eae1d46a45de412132da936f22cb5ce6f
3
- size 16166
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e402de054db900810ab3e9cc18ea3ff88fceefc9c2dab4578607c7c8b60714
3
+ size 18090