Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-da2-colab2

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
e29f7d5
·
verified ·
1 Parent(s): 29bc76f

Model save

Browse files
Files changed (3) hide show
  1. README.md +117 -0
  2. model.safetensors +1 -1
  3. runs/Dec03_16-02-28_53fb2934ed64/events.out.tfevents.1733241754.53fb2934ed64.9135.0 +2 -2
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: swinv2-tiny-patch4-window8-256-DMAE-da2-colab2
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: test
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.717391304347826
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # swinv2-tiny-patch4-window8-256-DMAE-da2-colab2
33
+
34
+ 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.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.7389
37
+ - Accuracy: 0.7174
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 1.5e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 64
62
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
+ - lr_scheduler_type: linear
64
+ - num_epochs: 40
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | 1.3473 | 0.9565 | 11 | 1.3763 | 0.2609 |
71
+ | 1.2385 | 1.9348 | 22 | 1.2596 | 0.5 |
72
+ | 1.1683 | 2.9130 | 33 | 1.2476 | 0.5 |
73
+ | 1.0809 | 3.9783 | 45 | 1.1625 | 0.5435 |
74
+ | 1.0147 | 4.9565 | 56 | 1.0490 | 0.5435 |
75
+ | 0.9755 | 5.9348 | 67 | 0.9155 | 0.6739 |
76
+ | 0.89 | 6.9130 | 78 | 0.9343 | 0.6304 |
77
+ | 0.832 | 7.9783 | 90 | 0.7973 | 0.6522 |
78
+ | 0.7846 | 8.9565 | 101 | 0.8325 | 0.6087 |
79
+ | 0.74 | 9.9348 | 112 | 0.8328 | 0.6087 |
80
+ | 0.679 | 10.9130 | 123 | 0.7195 | 0.7174 |
81
+ | 0.6487 | 11.9783 | 135 | 0.6740 | 0.7826 |
82
+ | 0.6774 | 12.9565 | 146 | 0.7157 | 0.6957 |
83
+ | 0.5727 | 13.9348 | 157 | 0.6934 | 0.7174 |
84
+ | 0.5872 | 14.9130 | 168 | 0.7335 | 0.6739 |
85
+ | 0.6116 | 15.9783 | 180 | 0.6892 | 0.7609 |
86
+ | 0.5783 | 16.9565 | 191 | 0.6796 | 0.7174 |
87
+ | 0.5658 | 17.9348 | 202 | 0.6966 | 0.7609 |
88
+ | 0.5447 | 18.9130 | 213 | 0.6708 | 0.7174 |
89
+ | 0.5452 | 19.9783 | 225 | 0.7297 | 0.6957 |
90
+ | 0.509 | 20.9565 | 236 | 0.7137 | 0.6522 |
91
+ | 0.527 | 21.9348 | 247 | 0.7047 | 0.7174 |
92
+ | 0.5382 | 22.9130 | 258 | 0.7737 | 0.6739 |
93
+ | 0.508 | 23.9783 | 270 | 0.7073 | 0.7174 |
94
+ | 0.4579 | 24.9565 | 281 | 0.7355 | 0.6739 |
95
+ | 0.492 | 25.9348 | 292 | 0.7152 | 0.7174 |
96
+ | 0.4273 | 26.9130 | 303 | 0.7243 | 0.7174 |
97
+ | 0.4823 | 27.9783 | 315 | 0.7477 | 0.6739 |
98
+ | 0.4659 | 28.9565 | 326 | 0.7193 | 0.6957 |
99
+ | 0.4401 | 29.9348 | 337 | 0.7509 | 0.6957 |
100
+ | 0.4717 | 30.9130 | 348 | 0.7327 | 0.6957 |
101
+ | 0.4139 | 31.9783 | 360 | 0.7041 | 0.7174 |
102
+ | 0.4365 | 32.9565 | 371 | 0.7286 | 0.6957 |
103
+ | 0.4088 | 33.9348 | 382 | 0.7495 | 0.7174 |
104
+ | 0.4505 | 34.9130 | 393 | 0.7399 | 0.7174 |
105
+ | 0.4143 | 35.9783 | 405 | 0.7160 | 0.7174 |
106
+ | 0.4093 | 36.9565 | 416 | 0.7210 | 0.7174 |
107
+ | 0.43 | 37.9348 | 427 | 0.7342 | 0.7174 |
108
+ | 0.424 | 38.9130 | 438 | 0.7386 | 0.7174 |
109
+ | 0.4169 | 39.1087 | 440 | 0.7389 | 0.7174 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.46.2
115
+ - Pytorch 2.5.1+cu121
116
+ - Datasets 3.1.0
117
+ - Tokenizers 0.20.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:602b3d9850e46a341aa028e590401ae1541b54eab1ec1d8300b1eb9c63bcb38f
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfb498179ba28553ca67a4e7809315ab2af87e5fd0b11750c1bb889b8adfbb4
3
  size 110356296
runs/Dec03_16-02-28_53fb2934ed64/events.out.tfevents.1733241754.53fb2934ed64.9135.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a304d3f04a8b6ed9293a4c9e77f4a86c86268e029ed74d8bd516cec3c4a322
3
- size 27438
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7252d5e41a7690c608f716a0c903e66c3c707d3590a52d680ba6c133f9c0e4b2
3
+ size 28115