Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV50

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
RobertoSonic commited on
Commit
7017b52
·
verified ·
1 Parent(s): 9af377a

Model save

Browse files
Files changed (3) hide show
  1. README.md +96 -0
  2. model.safetensors +1 -1
  3. runs/Feb09_20-05-06_e92dafee4e15/events.out.tfevents.1739131517.e92dafee4e15.2938.0 +2 -2
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swinv2-tiny-patch4-window8-256-dmae-humeda-DAV50
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # swinv2-tiny-patch4-window8-256-dmae-humeda-DAV50
18
+
19
+ 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.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.8008
22
+ - Accuracy: 0.7159
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1.5e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine_with_restarts
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 40
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
57
+ | No log | 1.0 | 5 | 1.5451 | 0.3864 |
58
+ | No log | 2.0 | 10 | 1.5220 | 0.3864 |
59
+ | 1.4177 | 3.0 | 15 | 1.4938 | 0.4205 |
60
+ | 1.4177 | 4.0 | 20 | 1.4111 | 0.4432 |
61
+ | 1.2671 | 5.0 | 25 | 1.2941 | 0.4545 |
62
+ | 1.2671 | 6.0 | 30 | 1.2036 | 0.4545 |
63
+ | 1.2671 | 7.0 | 35 | 1.0816 | 0.5114 |
64
+ | 0.9869 | 8.0 | 40 | 1.0452 | 0.5795 |
65
+ | 0.9869 | 9.0 | 45 | 0.9876 | 0.625 |
66
+ | 0.8456 | 10.0 | 50 | 0.9791 | 0.5909 |
67
+ | 0.8456 | 11.0 | 55 | 0.9662 | 0.6023 |
68
+ | 0.7126 | 12.0 | 60 | 0.9302 | 0.6364 |
69
+ | 0.7126 | 13.0 | 65 | 0.9379 | 0.625 |
70
+ | 0.7126 | 14.0 | 70 | 0.9036 | 0.6705 |
71
+ | 0.6561 | 15.0 | 75 | 0.8846 | 0.6591 |
72
+ | 0.6561 | 16.0 | 80 | 0.8689 | 0.6591 |
73
+ | 0.6367 | 17.0 | 85 | 0.8543 | 0.6591 |
74
+ | 0.6367 | 18.0 | 90 | 0.8342 | 0.6932 |
75
+ | 0.6367 | 19.0 | 95 | 0.8185 | 0.6705 |
76
+ | 0.5463 | 20.0 | 100 | 0.8290 | 0.7159 |
77
+ | 0.5463 | 21.0 | 105 | 0.8354 | 0.7273 |
78
+ | 0.5504 | 22.0 | 110 | 0.8160 | 0.7159 |
79
+ | 0.5504 | 23.0 | 115 | 0.8073 | 0.7159 |
80
+ | 0.507 | 24.0 | 120 | 0.8071 | 0.7045 |
81
+ | 0.507 | 25.0 | 125 | 0.8071 | 0.6932 |
82
+ | 0.507 | 26.0 | 130 | 0.8047 | 0.7045 |
83
+ | 0.5226 | 27.0 | 135 | 0.8000 | 0.7045 |
84
+ | 0.5226 | 28.0 | 140 | 0.7987 | 0.7159 |
85
+ | 0.5144 | 29.0 | 145 | 0.8000 | 0.7159 |
86
+ | 0.5144 | 30.0 | 150 | 0.8002 | 0.7159 |
87
+ | 0.5144 | 31.0 | 155 | 0.8008 | 0.7159 |
88
+ | 0.4862 | 32.0 | 160 | 0.8008 | 0.7159 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.48.2
94
+ - Pytorch 2.5.1+cu124
95
+ - Datasets 3.2.0
96
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a027b20033b615c86655e56b97c558570f932d4f5352cb2a18fd3074e941649a
3
  size 110359372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6f78a8894ec51994531c451c347ef305da5188497fd70523b91e9aa9ba7245
3
  size 110359372
runs/Feb09_20-05-06_e92dafee4e15/events.out.tfevents.1739131517.e92dafee4e15.2938.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5169fbdb1ae488830f41fb9a26c496eb963ebd8a43726df6cc9fc64dd77f152b
3
- size 18312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89315b774d777b978bf27576db28758b2d1a7413ef341e4d0f617f317458b56c
3
+ size 18989