Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-dmae-va-U5-42B

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
7c84eba
·
verified ·
1 Parent(s): 4c2f8c2

Model save

Browse files
Files changed (3) hide show
  1. README.md +100 -0
  2. model.safetensors +1 -1
  3. runs/Apr18_22-30-59_DESKTOP-SKBE9FB/events.out.tfevents.1713501061.DESKTOP-SKBE9FB.5296.0 +2 -2
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: swinv2-tiny-patch4-window8-256-dmae-va-U5-42B
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # swinv2-tiny-patch4-window8-256-dmae-va-U5-42B
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9372
21
+ - Accuracy: 0.5667
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 4e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 42
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 0.9 | 7 | 7.8663 | 0.1167 |
56
+ | 6.936 | 1.94 | 15 | 7.7572 | 0.1167 |
57
+ | 6.936 | 2.97 | 23 | 7.1789 | 0.1167 |
58
+ | 6.7016 | 4.0 | 31 | 5.9142 | 0.1167 |
59
+ | 5.5418 | 4.9 | 38 | 4.6065 | 0.1167 |
60
+ | 5.5418 | 5.94 | 46 | 3.2783 | 0.1167 |
61
+ | 3.6439 | 6.97 | 54 | 2.1984 | 0.1167 |
62
+ | 2.2477 | 8.0 | 62 | 1.5631 | 0.45 |
63
+ | 2.2477 | 8.9 | 69 | 1.3158 | 0.45 |
64
+ | 1.5076 | 9.94 | 77 | 1.3665 | 0.3333 |
65
+ | 1.3865 | 10.97 | 85 | 1.3561 | 0.35 |
66
+ | 1.3865 | 12.0 | 93 | 1.2673 | 0.4667 |
67
+ | 1.3436 | 12.9 | 100 | 1.5020 | 0.2833 |
68
+ | 1.3187 | 13.94 | 108 | 1.3018 | 0.4667 |
69
+ | 1.3187 | 14.97 | 116 | 1.2582 | 0.4833 |
70
+ | 1.2132 | 16.0 | 124 | 1.2250 | 0.5 |
71
+ | 1.2132 | 16.9 | 131 | 1.2071 | 0.5167 |
72
+ | 1.2041 | 17.94 | 139 | 1.1806 | 0.5167 |
73
+ | 1.1756 | 18.97 | 147 | 1.1720 | 0.55 |
74
+ | 1.1756 | 20.0 | 155 | 1.1319 | 0.5333 |
75
+ | 1.1107 | 20.9 | 162 | 1.0851 | 0.5833 |
76
+ | 1.0651 | 21.94 | 170 | 1.0554 | 0.5833 |
77
+ | 1.0651 | 22.97 | 178 | 1.0580 | 0.5 |
78
+ | 1.0419 | 24.0 | 186 | 1.1471 | 0.5833 |
79
+ | 0.9804 | 24.9 | 193 | 1.0633 | 0.6333 |
80
+ | 0.9804 | 25.94 | 201 | 1.0597 | 0.5833 |
81
+ | 0.9195 | 26.97 | 209 | 0.9563 | 0.6333 |
82
+ | 0.9053 | 28.0 | 217 | 0.9839 | 0.5167 |
83
+ | 0.9053 | 28.9 | 224 | 0.9914 | 0.5167 |
84
+ | 0.8645 | 29.94 | 232 | 0.9520 | 0.5833 |
85
+ | 0.8139 | 30.97 | 240 | 0.9573 | 0.5333 |
86
+ | 0.8139 | 32.0 | 248 | 0.9510 | 0.5167 |
87
+ | 0.8151 | 32.9 | 255 | 0.9469 | 0.5167 |
88
+ | 0.8151 | 33.94 | 263 | 0.9872 | 0.5333 |
89
+ | 0.7837 | 34.97 | 271 | 0.9279 | 0.5833 |
90
+ | 0.7659 | 36.0 | 279 | 0.9174 | 0.5667 |
91
+ | 0.7659 | 36.9 | 286 | 0.9347 | 0.5667 |
92
+ | 0.7835 | 37.94 | 294 | 0.9372 | 0.5667 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.36.2
98
+ - Pytorch 2.1.2+cu118
99
+ - Datasets 2.16.1
100
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f133ea2e80ec9d5d13b66f121048dc5ffe191d494405eb1a38ead4be063c4d99
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad66dfcfd2c83c82c4c0a62d4d25a3b2118b35a3eee806985d99b6b8ed16f9fe
3
  size 110356296
runs/Apr18_22-30-59_DESKTOP-SKBE9FB/events.out.tfevents.1713501061.DESKTOP-SKBE9FB.5296.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3d04ff42caf9a36180e90ffc20aa7aa768eb6649b7662fda0e30c29c2951965
3
- size 19934
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bc049110732904f6a1093a2c0de1d2e862d14ceedf4d1e38192c7e01b3a6fe
3
+ size 21091