Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV68

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Model card Files
xet
 Metrics Community
RobertoSonic commited on
Commit
e74f028
·
verified ·
1 Parent(s): 92c00aa

Model save

Browse files
Files changed (3) hide show
  1. README.md +107 -0
  2. model.safetensors +1 -1
  3. runs/Mar21_02-25-49_721b7bb2497f/events.out.tfevents.1742523970.721b7bb2497f.9420.0 +2 -2
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-DAV68
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-DAV68
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: 0.2897
22
+ - Accuracy: 0.9143
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: 3e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 64
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: 45
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
+ | 1.0651 | 1.0 | 18 | 1.0769 | 0.4686 |
58
+ | 0.9503 | 2.0 | 36 | 0.8111 | 0.7257 |
59
+ | 0.5745 | 3.0 | 54 | 0.4972 | 0.7314 |
60
+ | 0.4746 | 4.0 | 72 | 0.4788 | 0.7486 |
61
+ | 0.4363 | 5.0 | 90 | 0.5427 | 0.7314 |
62
+ | 0.4362 | 6.0 | 108 | 0.3581 | 0.8686 |
63
+ | 0.3476 | 7.0 | 126 | 0.3572 | 0.8686 |
64
+ | 0.3113 | 8.0 | 144 | 0.4335 | 0.7886 |
65
+ | 0.3943 | 9.0 | 162 | 0.2782 | 0.8686 |
66
+ | 0.2574 | 10.0 | 180 | 0.3320 | 0.8686 |
67
+ | 0.2345 | 11.0 | 198 | 0.4383 | 0.8343 |
68
+ | 0.3002 | 12.0 | 216 | 0.3053 | 0.8686 |
69
+ | 0.2038 | 13.0 | 234 | 0.3189 | 0.8743 |
70
+ | 0.2244 | 14.0 | 252 | 0.2766 | 0.8743 |
71
+ | 0.2277 | 15.0 | 270 | 0.2637 | 0.8857 |
72
+ | 0.2318 | 16.0 | 288 | 0.4612 | 0.8114 |
73
+ | 0.1908 | 17.0 | 306 | 0.3167 | 0.8857 |
74
+ | 0.1932 | 18.0 | 324 | 0.2949 | 0.9029 |
75
+ | 0.1676 | 19.0 | 342 | 0.2627 | 0.9086 |
76
+ | 0.1442 | 20.0 | 360 | 0.2584 | 0.9143 |
77
+ | 0.1606 | 21.0 | 378 | 0.2626 | 0.9143 |
78
+ | 0.1624 | 22.0 | 396 | 0.2351 | 0.9257 |
79
+ | 0.1735 | 23.0 | 414 | 0.2746 | 0.9257 |
80
+ | 0.1604 | 24.0 | 432 | 0.3237 | 0.8914 |
81
+ | 0.122 | 25.0 | 450 | 0.2852 | 0.8914 |
82
+ | 0.1447 | 26.0 | 468 | 0.2594 | 0.92 |
83
+ | 0.1265 | 27.0 | 486 | 0.2857 | 0.9029 |
84
+ | 0.1265 | 28.0 | 504 | 0.3238 | 0.8743 |
85
+ | 0.122 | 29.0 | 522 | 0.3029 | 0.8857 |
86
+ | 0.0929 | 30.0 | 540 | 0.2936 | 0.9029 |
87
+ | 0.1276 | 31.0 | 558 | 0.2777 | 0.9143 |
88
+ | 0.1118 | 32.0 | 576 | 0.2812 | 0.9143 |
89
+ | 0.1058 | 33.0 | 594 | 0.2925 | 0.92 |
90
+ | 0.0824 | 34.0 | 612 | 0.3519 | 0.8914 |
91
+ | 0.1084 | 35.0 | 630 | 0.2847 | 0.92 |
92
+ | 0.1074 | 36.0 | 648 | 0.2735 | 0.9143 |
93
+ | 0.1415 | 37.0 | 666 | 0.2724 | 0.9257 |
94
+ | 0.0702 | 38.0 | 684 | 0.2873 | 0.92 |
95
+ | 0.0987 | 39.0 | 702 | 0.2924 | 0.92 |
96
+ | 0.0637 | 40.0 | 720 | 0.2868 | 0.9314 |
97
+ | 0.1183 | 41.0 | 738 | 0.2892 | 0.92 |
98
+ | 0.096 | 42.0 | 756 | 0.2910 | 0.9143 |
99
+ | 0.0719 | 42.5217 | 765 | 0.2897 | 0.9143 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.49.0
105
+ - Pytorch 2.6.0+cu124
106
+ - Datasets 3.4.1
107
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45f1520058b82133e0659844b81433eb9437b64d69b95a3e1cd4c8105e2abd37
3
  size 110353212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b73febe4e0ffd01eb19ae40d9f9b4f5af17a1983fa5ca059d3fe2fd19f473a5
3
  size 110353212
runs/Mar21_02-25-49_721b7bb2497f/events.out.tfevents.1742523970.721b7bb2497f.9420.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6824901ecc6260fdefa341e4921b5372e24ec126bf3c940deb7cf3532b3324b8
3
- size 35170
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486f49be81472555d57d76b214eabb8fa8761951821824e2393f515e9069b6b7
3
+ size 35847