Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-ve-UH2

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
d5d11b8
•
1 Parent(s): 947e41b

Model save

Browse files
Files changed (2) hide show
  1. README.md +142 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: swinv2-tiny-patch4-window8-256-ve-UH2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # swinv2-tiny-patch4-window8-256-ve-UH2
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7415
21
+ - Accuracy: 0.6923
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 80
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 1.0 | 2 | 1.6091 | 0.4038 |
56
+ | No log | 2.0 | 4 | 1.6070 | 0.4231 |
57
+ | No log | 3.0 | 6 | 1.6017 | 0.4038 |
58
+ | No log | 4.0 | 8 | 1.5911 | 0.4038 |
59
+ | 1.6022 | 5.0 | 10 | 1.5707 | 0.4038 |
60
+ | 1.6022 | 6.0 | 12 | 1.5355 | 0.4038 |
61
+ | 1.6022 | 7.0 | 14 | 1.4951 | 0.4038 |
62
+ | 1.6022 | 8.0 | 16 | 1.4528 | 0.4038 |
63
+ | 1.6022 | 9.0 | 18 | 1.4096 | 0.4038 |
64
+ | 1.4645 | 10.0 | 20 | 1.3820 | 0.4038 |
65
+ | 1.4645 | 11.0 | 22 | 1.4055 | 0.4038 |
66
+ | 1.4645 | 12.0 | 24 | 1.3765 | 0.4038 |
67
+ | 1.4645 | 13.0 | 26 | 1.3820 | 0.4038 |
68
+ | 1.4645 | 14.0 | 28 | 1.3712 | 0.4038 |
69
+ | 1.3172 | 15.0 | 30 | 1.3546 | 0.4038 |
70
+ | 1.3172 | 16.0 | 32 | 1.3637 | 0.4038 |
71
+ | 1.3172 | 17.0 | 34 | 1.3646 | 0.4038 |
72
+ | 1.3172 | 18.0 | 36 | 1.3271 | 0.4038 |
73
+ | 1.3172 | 19.0 | 38 | 1.3084 | 0.4038 |
74
+ | 1.2549 | 20.0 | 40 | 1.3402 | 0.4038 |
75
+ | 1.2549 | 21.0 | 42 | 1.3550 | 0.4038 |
76
+ | 1.2549 | 22.0 | 44 | 1.2677 | 0.4038 |
77
+ | 1.2549 | 23.0 | 46 | 1.2093 | 0.4038 |
78
+ | 1.2549 | 24.0 | 48 | 1.2040 | 0.4231 |
79
+ | 1.2092 | 25.0 | 50 | 1.2963 | 0.4231 |
80
+ | 1.2092 | 26.0 | 52 | 1.2917 | 0.4808 |
81
+ | 1.2092 | 27.0 | 54 | 1.1798 | 0.5769 |
82
+ | 1.2092 | 28.0 | 56 | 1.1047 | 0.6346 |
83
+ | 1.2092 | 29.0 | 58 | 1.0923 | 0.6731 |
84
+ | 1.1321 | 30.0 | 60 | 1.1066 | 0.6538 |
85
+ | 1.1321 | 31.0 | 62 | 1.0874 | 0.6538 |
86
+ | 1.1321 | 32.0 | 64 | 1.0548 | 0.6731 |
87
+ | 1.1321 | 33.0 | 66 | 1.0012 | 0.6538 |
88
+ | 1.1321 | 34.0 | 68 | 0.9641 | 0.6923 |
89
+ | 1.0022 | 35.0 | 70 | 0.9796 | 0.6538 |
90
+ | 1.0022 | 36.0 | 72 | 0.9631 | 0.6538 |
91
+ | 1.0022 | 37.0 | 74 | 0.9040 | 0.6731 |
92
+ | 1.0022 | 38.0 | 76 | 0.8731 | 0.6923 |
93
+ | 1.0022 | 39.0 | 78 | 0.8960 | 0.6731 |
94
+ | 0.8941 | 40.0 | 80 | 0.9133 | 0.6538 |
95
+ | 0.8941 | 41.0 | 82 | 0.8507 | 0.6923 |
96
+ | 0.8941 | 42.0 | 84 | 0.8064 | 0.7115 |
97
+ | 0.8941 | 43.0 | 86 | 0.8075 | 0.7115 |
98
+ | 0.8941 | 44.0 | 88 | 0.8486 | 0.6923 |
99
+ | 0.7866 | 45.0 | 90 | 0.8075 | 0.6923 |
100
+ | 0.7866 | 46.0 | 92 | 0.7496 | 0.6731 |
101
+ | 0.7866 | 47.0 | 94 | 0.7431 | 0.6731 |
102
+ | 0.7866 | 48.0 | 96 | 0.7442 | 0.6731 |
103
+ | 0.7866 | 49.0 | 98 | 0.7735 | 0.6923 |
104
+ | 0.7281 | 50.0 | 100 | 0.7751 | 0.6923 |
105
+ | 0.7281 | 51.0 | 102 | 0.7370 | 0.6923 |
106
+ | 0.7281 | 52.0 | 104 | 0.7230 | 0.6923 |
107
+ | 0.7281 | 53.0 | 106 | 0.7314 | 0.6923 |
108
+ | 0.7281 | 54.0 | 108 | 0.7498 | 0.6731 |
109
+ | 0.6725 | 55.0 | 110 | 0.7557 | 0.6731 |
110
+ | 0.6725 | 56.0 | 112 | 0.7314 | 0.7115 |
111
+ | 0.6725 | 57.0 | 114 | 0.7334 | 0.7115 |
112
+ | 0.6725 | 58.0 | 116 | 0.7375 | 0.7115 |
113
+ | 0.6725 | 59.0 | 118 | 0.7434 | 0.6923 |
114
+ | 0.6526 | 60.0 | 120 | 0.7548 | 0.6731 |
115
+ | 0.6526 | 61.0 | 122 | 0.7813 | 0.7115 |
116
+ | 0.6526 | 62.0 | 124 | 0.7722 | 0.6923 |
117
+ | 0.6526 | 63.0 | 126 | 0.7469 | 0.6923 |
118
+ | 0.6526 | 64.0 | 128 | 0.7402 | 0.6731 |
119
+ | 0.5915 | 65.0 | 130 | 0.7448 | 0.7308 |
120
+ | 0.5915 | 66.0 | 132 | 0.7467 | 0.6923 |
121
+ | 0.5915 | 67.0 | 134 | 0.7496 | 0.6731 |
122
+ | 0.5915 | 68.0 | 136 | 0.7518 | 0.7308 |
123
+ | 0.5915 | 69.0 | 138 | 0.7453 | 0.7115 |
124
+ | 0.578 | 70.0 | 140 | 0.7385 | 0.6923 |
125
+ | 0.578 | 71.0 | 142 | 0.7411 | 0.6731 |
126
+ | 0.578 | 72.0 | 144 | 0.7442 | 0.6731 |
127
+ | 0.578 | 73.0 | 146 | 0.7440 | 0.6731 |
128
+ | 0.578 | 74.0 | 148 | 0.7428 | 0.6923 |
129
+ | 0.5826 | 75.0 | 150 | 0.7414 | 0.6923 |
130
+ | 0.5826 | 76.0 | 152 | 0.7416 | 0.6923 |
131
+ | 0.5826 | 77.0 | 154 | 0.7414 | 0.6923 |
132
+ | 0.5826 | 78.0 | 156 | 0.7413 | 0.6731 |
133
+ | 0.5826 | 79.0 | 158 | 0.7413 | 0.6731 |
134
+ | 0.5586 | 80.0 | 160 | 0.7415 | 0.6923 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - Transformers 4.36.2
140
+ - Pytorch 2.1.2+cu118
141
+ - Datasets 2.16.1
142
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e772b63a666ca8d67593b4f924b3560e59373cc01108c89fbea7f4285069b91
3
  size 110359372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73277872eadc60b53407042236bb2a71e0bac0239d0cc9fb98f94ca8e5e280b5
3
  size 110359372