Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-5e-1

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
838ae87
·
verified ·
1 Parent(s): 72a5345

Model save

Browse files
Files changed (3) hide show
  1. README.md +111 -0
  2. model.safetensors +1 -1
  3. runs/Dec02_15-23-48_DESKTOP-SKBE9FB/events.out.tfevents.1733174631.DESKTOP-SKBE9FB.6524.0 +2 -2
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: swinv2-tiny-patch4-window8-256-DMAE-5e-1
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
+ # swinv2-tiny-patch4-window8-256-DMAE-5e-1
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: 1.2338
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: 0.5
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
+ - num_epochs: 40
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.86 | 3 | 343.8003 | 0.3261 |
70
+ | No log | 2.0 | 7 | 1260.1489 | 0.1087 |
71
+ | 517.6714 | 2.86 | 10 | 457.5103 | 0.3261 |
72
+ | 517.6714 | 4.0 | 14 | 180.1205 | 0.1087 |
73
+ | 517.6714 | 4.86 | 17 | 190.9627 | 0.1087 |
74
+ | 201.7487 | 6.0 | 21 | 54.3349 | 0.4565 |
75
+ | 201.7487 | 6.86 | 24 | 70.2849 | 0.3261 |
76
+ | 201.7487 | 8.0 | 28 | 57.7033 | 0.3261 |
77
+ | 64.7194 | 8.86 | 31 | 115.5257 | 0.1087 |
78
+ | 64.7194 | 10.0 | 35 | 72.7990 | 0.3261 |
79
+ | 64.7194 | 10.86 | 38 | 41.8670 | 0.4565 |
80
+ | 58.6249 | 12.0 | 42 | 26.2765 | 0.4565 |
81
+ | 58.6249 | 12.86 | 45 | 41.7245 | 0.3261 |
82
+ | 58.6249 | 14.0 | 49 | 23.6962 | 0.4565 |
83
+ | 49.7372 | 14.86 | 52 | 13.4265 | 0.3261 |
84
+ | 49.7372 | 16.0 | 56 | 7.0405 | 0.4565 |
85
+ | 49.7372 | 16.86 | 59 | 5.0777 | 0.4565 |
86
+ | 11.7669 | 18.0 | 63 | 13.5690 | 0.4565 |
87
+ | 11.7669 | 18.86 | 66 | 5.5425 | 0.1087 |
88
+ | 13.3323 | 20.0 | 70 | 6.4491 | 0.4565 |
89
+ | 13.3323 | 20.86 | 73 | 7.3066 | 0.3261 |
90
+ | 13.3323 | 22.0 | 77 | 10.8431 | 0.4565 |
91
+ | 9.2763 | 22.86 | 80 | 12.1588 | 0.3261 |
92
+ | 9.2763 | 24.0 | 84 | 5.4926 | 0.4565 |
93
+ | 9.2763 | 24.86 | 87 | 4.4689 | 0.3261 |
94
+ | 6.8526 | 26.0 | 91 | 3.7880 | 0.4565 |
95
+ | 6.8526 | 26.86 | 94 | 2.3297 | 0.4565 |
96
+ | 6.8526 | 28.0 | 98 | 2.8532 | 0.4565 |
97
+ | 3.0687 | 28.86 | 101 | 2.6943 | 0.1087 |
98
+ | 3.0687 | 30.0 | 105 | 2.0957 | 0.3261 |
99
+ | 3.0687 | 30.86 | 108 | 1.4001 | 0.4565 |
100
+ | 2.1059 | 32.0 | 112 | 1.3081 | 0.3261 |
101
+ | 2.1059 | 32.86 | 115 | 1.2392 | 0.3261 |
102
+ | 2.1059 | 34.0 | 119 | 1.2510 | 0.4565 |
103
+ | 1.3417 | 34.29 | 120 | 1.2338 | 0.4565 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.36.2
109
+ - Pytorch 2.1.2+cu118
110
+ - Datasets 2.16.1
111
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17845c585c9329778012adb94b0ad559dc0fb3203e1c97d888cdadb9cabaefdf
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f1d71670c5c61d2d2ed32d43ada7083fd20e0159953b666b4288af90e2ba9b5
3
  size 110356296
runs/Dec02_15-23-48_DESKTOP-SKBE9FB/events.out.tfevents.1733174631.DESKTOP-SKBE9FB.6524.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c017c3afe394786f3f4a306a30e22de3eaa14d98b9959105ae0f87b6de6c65a2
3
- size 15535
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f98ed45403331b34e269af005c10751e8092070b89bce8d283c4bc3096c5f7
3
+ size 18093