Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV23

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
RobertoSonic commited on
Commit
fbb7e32
·
verified ·
1 Parent(s): eb1e4fa

Model save

Browse files
Files changed (3) hide show
  1. README.md +101 -0
  2. model.safetensors +1 -1
  3. runs/Jan23_23-06-31_ad4119443856/events.out.tfevents.1737673619.ad4119443856.2989.0 +2 -2
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-DAV23
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-DAV23
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: 1.1930
22
+ - Accuracy: 0.7765
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: 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: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 40
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
56
+ | 6.4493 | 1.0 | 17 | 1.5281 | 0.2941 |
57
+ | 5.7922 | 2.0 | 34 | 1.3176 | 0.3882 |
58
+ | 4.2502 | 3.0 | 51 | 1.2015 | 0.4353 |
59
+ | 3.2402 | 4.0 | 68 | 0.8902 | 0.7176 |
60
+ | 2.5386 | 5.0 | 85 | 0.6509 | 0.7765 |
61
+ | 2.0351 | 6.0 | 102 | 0.6759 | 0.7647 |
62
+ | 1.8225 | 7.0 | 119 | 0.6607 | 0.7765 |
63
+ | 1.4778 | 8.0 | 136 | 0.7162 | 0.7529 |
64
+ | 1.4076 | 9.0 | 153 | 0.9084 | 0.7294 |
65
+ | 1.2056 | 10.0 | 170 | 0.6901 | 0.8118 |
66
+ | 0.9552 | 11.0 | 187 | 0.9153 | 0.7765 |
67
+ | 0.9859 | 12.0 | 204 | 0.8694 | 0.7529 |
68
+ | 0.8309 | 13.0 | 221 | 0.7666 | 0.8 |
69
+ | 0.7722 | 14.0 | 238 | 0.9118 | 0.7529 |
70
+ | 0.7632 | 15.0 | 255 | 0.8953 | 0.7529 |
71
+ | 0.5868 | 16.0 | 272 | 0.9678 | 0.7529 |
72
+ | 0.6577 | 17.0 | 289 | 1.0503 | 0.7765 |
73
+ | 0.5816 | 18.0 | 306 | 1.0602 | 0.7294 |
74
+ | 0.6222 | 19.0 | 323 | 1.1543 | 0.7765 |
75
+ | 0.4861 | 20.0 | 340 | 0.9739 | 0.8118 |
76
+ | 0.4422 | 21.0 | 357 | 1.0354 | 0.8 |
77
+ | 0.506 | 22.0 | 374 | 1.1097 | 0.8118 |
78
+ | 0.3833 | 23.0 | 391 | 1.2009 | 0.7765 |
79
+ | 0.4574 | 24.0 | 408 | 1.1366 | 0.7765 |
80
+ | 0.4467 | 25.0 | 425 | 1.0601 | 0.8118 |
81
+ | 0.4451 | 26.0 | 442 | 1.0935 | 0.7765 |
82
+ | 0.4384 | 27.0 | 459 | 1.1617 | 0.7647 |
83
+ | 0.4321 | 28.0 | 476 | 1.1012 | 0.7765 |
84
+ | 0.4398 | 29.0 | 493 | 1.0825 | 0.7882 |
85
+ | 0.361 | 30.0 | 510 | 1.1127 | 0.7647 |
86
+ | 0.4428 | 31.0 | 527 | 1.2024 | 0.7529 |
87
+ | 0.451 | 32.0 | 544 | 1.1550 | 0.7647 |
88
+ | 0.403 | 33.0 | 561 | 1.1646 | 0.7765 |
89
+ | 0.3059 | 34.0 | 578 | 1.2442 | 0.7765 |
90
+ | 0.3022 | 35.0 | 595 | 1.1976 | 0.7765 |
91
+ | 0.319 | 36.0 | 612 | 1.1564 | 0.7765 |
92
+ | 0.3737 | 37.0 | 629 | 1.1857 | 0.7765 |
93
+ | 0.3063 | 37.6667 | 640 | 1.1930 | 0.7765 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.47.1
99
+ - Pytorch 2.5.1+cu121
100
+ - Datasets 3.2.0
101
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e27a2b1c308c21b728e82ff89a52852b71e7592a8df4a412547ecfbfa370dd51
3
  size 110359372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5e89e9714da021731a0f6170af7db5e84fcf13ad5ce50db1639283db298c5d
3
  size 110359372
runs/Jan23_23-06-31_ad4119443856/events.out.tfevents.1737673619.ad4119443856.2989.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc870a3c399db0938e372a9b2586367856fc9e24c2d71a55ca51cf75473438c6
3
- size 28782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a938065d0a9a8cc9d2ca083649170452d6069dd6c3f8a1095a3f516e15a9bc
3
+ size 29459