Hugging Face's logo

RobertoSonic
/
swinv2-tiny-patch4-window8-256-dmae-humeda-DAV56

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Model card Files
xet
 Metrics Community
RobertoSonic commited on
Commit
da973b2
·
verified ·
1 Parent(s): 78089d8

Model save

Browse files
Files changed (3) hide show
  1. README.md +109 -0
  2. model.safetensors +1 -1
  3. runs/Feb10_02-57-08_e3629502e642/events.out.tfevents.1739156237.e3629502e642.69539.0 +2 -2
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-DAV56
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-DAV56
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: 0.8741
22
+ - Accuracy: 0.7308
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: 2e-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: 45
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
+ | No log | 0.8421 | 4 | 1.5618 | 0.3269 |
58
+ | No log | 1.8421 | 8 | 1.5396 | 0.4423 |
59
+ | 1.7209 | 2.8421 | 12 | 1.5124 | 0.3077 |
60
+ | 1.7209 | 3.8421 | 16 | 1.4679 | 0.3269 |
61
+ | 1.7209 | 4.8421 | 20 | 1.4130 | 0.3462 |
62
+ | 1.5864 | 5.8421 | 24 | 1.3107 | 0.5385 |
63
+ | 1.5864 | 6.8421 | 28 | 1.2112 | 0.5385 |
64
+ | 1.5864 | 7.8421 | 32 | 1.1194 | 0.5962 |
65
+ | 1.2629 | 8.8421 | 36 | 1.0422 | 0.5962 |
66
+ | 1.2629 | 9.8421 | 40 | 0.9706 | 0.6538 |
67
+ | 1.2629 | 10.8421 | 44 | 0.9638 | 0.6538 |
68
+ | 0.951 | 11.8421 | 48 | 0.9906 | 0.6154 |
69
+ | 0.951 | 12.8421 | 52 | 0.9890 | 0.5962 |
70
+ | 0.951 | 13.8421 | 56 | 0.9110 | 0.6538 |
71
+ | 0.7947 | 14.8421 | 60 | 0.9282 | 0.6731 |
72
+ | 0.7947 | 15.8421 | 64 | 0.9315 | 0.6538 |
73
+ | 0.7947 | 16.8421 | 68 | 0.9230 | 0.6154 |
74
+ | 0.7143 | 17.8421 | 72 | 0.9068 | 0.6538 |
75
+ | 0.7143 | 18.8421 | 76 | 0.8997 | 0.6154 |
76
+ | 0.7143 | 19.8421 | 80 | 0.8648 | 0.6923 |
77
+ | 0.6329 | 20.8421 | 84 | 0.8624 | 0.6538 |
78
+ | 0.6329 | 21.8421 | 88 | 0.8737 | 0.6154 |
79
+ | 0.6329 | 22.8421 | 92 | 0.8636 | 0.6731 |
80
+ | 0.5508 | 23.8421 | 96 | 0.8545 | 0.6538 |
81
+ | 0.5508 | 24.8421 | 100 | 0.8617 | 0.6731 |
82
+ | 0.5508 | 25.8421 | 104 | 0.8635 | 0.6346 |
83
+ | 0.5009 | 26.8421 | 108 | 0.8650 | 0.6346 |
84
+ | 0.5009 | 27.8421 | 112 | 0.8638 | 0.6538 |
85
+ | 0.5009 | 28.8421 | 116 | 0.8730 | 0.6538 |
86
+ | 0.5286 | 29.8421 | 120 | 0.8886 | 0.6346 |
87
+ | 0.5286 | 30.8421 | 124 | 0.8827 | 0.6538 |
88
+ | 0.5286 | 31.8421 | 128 | 0.8748 | 0.7308 |
89
+ | 0.4559 | 32.8421 | 132 | 0.8671 | 0.7115 |
90
+ | 0.4559 | 33.8421 | 136 | 0.8727 | 0.6731 |
91
+ | 0.4559 | 34.8421 | 140 | 0.8755 | 0.7115 |
92
+ | 0.4704 | 35.8421 | 144 | 0.8760 | 0.7308 |
93
+ | 0.4704 | 36.8421 | 148 | 0.8786 | 0.7308 |
94
+ | 0.4704 | 37.8421 | 152 | 0.8781 | 0.7308 |
95
+ | 0.4582 | 38.8421 | 156 | 0.8771 | 0.7308 |
96
+ | 0.4582 | 39.8421 | 160 | 0.8754 | 0.7308 |
97
+ | 0.4582 | 40.8421 | 164 | 0.8741 | 0.7308 |
98
+ | 0.4538 | 41.8421 | 168 | 0.8742 | 0.7308 |
99
+ | 0.4538 | 42.8421 | 172 | 0.8740 | 0.7308 |
100
+ | 0.4538 | 43.8421 | 176 | 0.8740 | 0.7308 |
101
+ | 0.4476 | 44.8421 | 180 | 0.8741 | 0.7308 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.48.2
107
+ - Pytorch 2.5.1+cu124
108
+ - Datasets 3.2.0
109
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a4acc688586ada3aaab877e5e27a44dd2e8ac61b024367639085b29cf1ffa23
3
  size 110359372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a82c088054a8cd16bb3f3bb24616dddf06aa1428a4552b5b77bc05a8d96622
3
  size 110359372
runs/Feb10_02-57-08_e3629502e642/events.out.tfevents.1739156237.e3629502e642.69539.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80469f38078ffe3f94c54a7a731b60acb3b6726b07fb25a4e9ea58905c1f27db
3
- size 22684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2136a6ba0ab94ef83e969dca39770e8898bb682c4e173c92942f7fa75411d9d9
3
+ size 23572