Hugging Face's logo

Augusto777
/
SW2-DMAE

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
Augusto777 commited on
Commit
1237de6
·
verified ·
1 Parent(s): 7c3e39f

Model save

Browse files
Files changed (3) hide show
  1. README.md +112 -0
  2. model.safetensors +1 -1
  3. runs/Dec03_17-08-30_DESKTOP-SKBE9FB/events.out.tfevents.1733267321.DESKTOP-SKBE9FB.21168.0 +2 -2
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: SW2-DMAE
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.45652173913043476
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # SW2-DMAE
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: 1.2088
36
+ - Accuracy: 0.4565
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
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
59
+ - gradient_accumulation_steps: 4
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 | 7.9402 | 0.1087 |
71
+ | No log | 2.0 | 7 | 7.9103 | 0.1087 |
72
+ | 7.944 | 2.86 | 10 | 7.8273 | 0.1087 |
73
+ | 7.944 | 4.0 | 14 | 7.4556 | 0.1087 |
74
+ | 7.944 | 4.86 | 17 | 7.0147 | 0.1087 |
75
+ | 7.2884 | 6.0 | 21 | 6.3290 | 0.1087 |
76
+ | 7.2884 | 6.86 | 24 | 5.8362 | 0.1087 |
77
+ | 7.2884 | 8.0 | 28 | 5.1955 | 0.1087 |
78
+ | 5.6818 | 8.86 | 31 | 4.7393 | 0.1087 |
79
+ | 5.6818 | 10.0 | 35 | 4.1698 | 0.1087 |
80
+ | 5.6818 | 10.86 | 38 | 3.7678 | 0.1087 |
81
+ | 4.3923 | 12.0 | 42 | 3.2683 | 0.1087 |
82
+ | 4.3923 | 12.86 | 45 | 2.9314 | 0.1087 |
83
+ | 4.3923 | 14.0 | 49 | 2.5362 | 0.1087 |
84
+ | 3.0666 | 14.86 | 52 | 2.2842 | 0.1087 |
85
+ | 3.0666 | 16.0 | 56 | 2.0075 | 0.1087 |
86
+ | 3.0666 | 16.86 | 59 | 1.8426 | 0.1087 |
87
+ | 2.1462 | 18.0 | 63 | 1.6712 | 0.4565 |
88
+ | 2.1462 | 18.86 | 66 | 1.5719 | 0.4565 |
89
+ | 1.6612 | 20.0 | 70 | 1.4659 | 0.4565 |
90
+ | 1.6612 | 20.86 | 73 | 1.4003 | 0.4565 |
91
+ | 1.6612 | 22.0 | 77 | 1.3301 | 0.4565 |
92
+ | 1.3809 | 22.86 | 80 | 1.2896 | 0.4565 |
93
+ | 1.3809 | 24.0 | 84 | 1.2505 | 0.4565 |
94
+ | 1.3809 | 24.86 | 87 | 1.2316 | 0.4565 |
95
+ | 1.2478 | 26.0 | 91 | 1.2170 | 0.4565 |
96
+ | 1.2478 | 26.86 | 94 | 1.2122 | 0.4565 |
97
+ | 1.2478 | 28.0 | 98 | 1.2116 | 0.4565 |
98
+ | 1.2118 | 28.86 | 101 | 1.2110 | 0.4565 |
99
+ | 1.2118 | 30.0 | 105 | 1.2108 | 0.4565 |
100
+ | 1.2118 | 30.86 | 108 | 1.2102 | 0.4565 |
101
+ | 1.1877 | 32.0 | 112 | 1.2095 | 0.4565 |
102
+ | 1.1877 | 32.86 | 115 | 1.2091 | 0.4565 |
103
+ | 1.1877 | 34.0 | 119 | 1.2088 | 0.4565 |
104
+ | 1.213 | 34.29 | 120 | 1.2088 | 0.4565 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.36.2
110
+ - Pytorch 2.1.2+cu118
111
+ - Datasets 2.16.1
112
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9633d7153c87ce12b5522e891bb045f300efc7c29774bc803542bce0e9f4b7
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea1845f08191139f0c49c08b0cab3350781be71b15bd8e6796d7cefb650d755
3
  size 110356296
runs/Dec03_17-08-30_DESKTOP-SKBE9FB/events.out.tfevents.1733267321.DESKTOP-SKBE9FB.21168.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dfa638e033a9baec4d78aff53b6082cf70e905392675359e056d68d2366b57a
3
- size 17182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8810815bac5c5a7b1ca58fd015af8faebd9453935ed02452df82cd09f5f916
3
+ size 18001