RobertoSonic commited on
Commit
ed655ec
·
verified ·
1 Parent(s): 2070d62

Model save

Browse files
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-DAV36
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-DAV36
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: 2.6972
22
+ - Accuracy: 0.68
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: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 32
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
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 30
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 3.214 | 1.0 | 22 | 1.4507 | 0.46 |
57
+ | 2.298 | 2.0 | 44 | 1.0632 | 0.62 |
58
+ | 0.9579 | 3.0 | 66 | 1.1191 | 0.64 |
59
+ | 0.4479 | 4.0 | 88 | 0.9825 | 0.6467 |
60
+ | 0.1963 | 5.0 | 110 | 1.2844 | 0.6467 |
61
+ | 0.1663 | 6.0 | 132 | 1.2373 | 0.6667 |
62
+ | 0.1188 | 7.0 | 154 | 1.4338 | 0.6933 |
63
+ | 0.0526 | 8.0 | 176 | 1.6726 | 0.7133 |
64
+ | 0.01 | 9.0 | 198 | 2.5248 | 0.6267 |
65
+ | 0.028 | 10.0 | 220 | 2.6156 | 0.6467 |
66
+ | 0.0296 | 11.0 | 242 | 2.8334 | 0.6533 |
67
+ | 0.0074 | 12.0 | 264 | 2.2200 | 0.6867 |
68
+ | 0.0022 | 13.0 | 286 | 2.2802 | 0.7467 |
69
+ | 0.0225 | 14.0 | 308 | 2.1764 | 0.6933 |
70
+ | 0.0058 | 15.0 | 330 | 3.0594 | 0.62 |
71
+ | 0.0075 | 16.0 | 352 | 3.2166 | 0.6333 |
72
+ | 0.0163 | 17.0 | 374 | 2.4014 | 0.6933 |
73
+ | 0.0033 | 18.0 | 396 | 2.9112 | 0.6733 |
74
+ | 0.0036 | 19.0 | 418 | 2.8147 | 0.6533 |
75
+ | 0.0033 | 20.0 | 440 | 2.7731 | 0.6733 |
76
+ | 0.0161 | 21.0 | 462 | 2.0340 | 0.7467 |
77
+ | 0.0012 | 22.0 | 484 | 2.4596 | 0.6867 |
78
+ | 0.0009 | 23.0 | 506 | 2.7352 | 0.6667 |
79
+ | 0.0101 | 24.0 | 528 | 2.8204 | 0.6667 |
80
+ | 0.0011 | 25.0 | 550 | 2.8091 | 0.6733 |
81
+ | 0.0005 | 26.0 | 572 | 2.8126 | 0.6667 |
82
+ | 0.0007 | 27.0 | 594 | 2.7742 | 0.6733 |
83
+ | 0.0004 | 28.0 | 616 | 2.7208 | 0.6733 |
84
+ | 0.0025 | 29.0 | 638 | 2.7022 | 0.6733 |
85
+ | 0.0025 | 30.0 | 660 | 2.6972 | 0.68 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.47.1
91
+ - Pytorch 2.5.1+cu121
92
+ - Datasets 3.2.0
93
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ced80f51f97e5e593eb52b89f40f5abe63d9114b188b1d648fe694caf1edc65f
3
  size 110359372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde4c5947f466de23ff081bf080627c15b5741a6815bc81d7a71827daf588188
3
  size 110359372
runs/Jan29_08-12-33_eaff62e1ff5e/events.out.tfevents.1738138363.eaff62e1ff5e.409.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b624239f768c402e3448bee520133ace4a08f568f328612b722e97ff8d367c60
3
- size 26619
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e4a3eba20267bffc11f6bff378f38dfdf0ef57d752f37f54705cb0c0cb7481
3
+ size 27296