Hugging Face's logo

Augusto777
/
vit-base-patch16-224-ve-b-U10-40

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
b19fd31
•
1 Parent(s): 5eb9128

Model save

Browse files
Files changed (3) hide show
  1. README.md +116 -0
  2. model.safetensors +1 -1
  3. runs/Jun11_17-06-33_DESKTOP-SKBE9FB/events.out.tfevents.1718147195.DESKTOP-SKBE9FB.9452.0 +2 -2
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-patch16-224-ve-b-U10-40
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.803921568627451
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # vit-base-patch16-224-ve-b-U10-40
32
+
33
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.6169
36
+ - Accuracy: 0.8039
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5.5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.05
64
+ - num_epochs: 40
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.96 | 6 | 1.3845 | 0.2549 |
71
+ | 1.3817 | 1.92 | 12 | 1.3529 | 0.4706 |
72
+ | 1.3817 | 2.88 | 18 | 1.2772 | 0.5882 |
73
+ | 1.2986 | 4.0 | 25 | 1.2121 | 0.3922 |
74
+ | 1.1298 | 4.96 | 31 | 1.1164 | 0.5882 |
75
+ | 1.1298 | 5.92 | 37 | 1.0879 | 0.5882 |
76
+ | 0.9842 | 6.88 | 43 | 0.9898 | 0.6863 |
77
+ | 0.8402 | 8.0 | 50 | 0.9233 | 0.7843 |
78
+ | 0.8402 | 8.96 | 56 | 0.9650 | 0.6471 |
79
+ | 0.7084 | 9.92 | 62 | 0.8243 | 0.7451 |
80
+ | 0.7084 | 10.88 | 68 | 0.7988 | 0.7647 |
81
+ | 0.5914 | 12.0 | 75 | 0.8114 | 0.7451 |
82
+ | 0.461 | 12.96 | 81 | 0.7652 | 0.7451 |
83
+ | 0.461 | 13.92 | 87 | 0.7406 | 0.7451 |
84
+ | 0.3769 | 14.88 | 93 | 0.6916 | 0.7451 |
85
+ | 0.3376 | 16.0 | 100 | 0.6182 | 0.7843 |
86
+ | 0.3376 | 16.96 | 106 | 0.8395 | 0.6863 |
87
+ | 0.2606 | 17.92 | 112 | 0.6941 | 0.7255 |
88
+ | 0.2606 | 18.88 | 118 | 0.7345 | 0.7255 |
89
+ | 0.2314 | 20.0 | 125 | 0.7374 | 0.7059 |
90
+ | 0.1907 | 20.96 | 131 | 0.7490 | 0.7647 |
91
+ | 0.1907 | 21.92 | 137 | 0.7292 | 0.7255 |
92
+ | 0.1804 | 22.88 | 143 | 0.7301 | 0.7451 |
93
+ | 0.1447 | 24.0 | 150 | 0.7224 | 0.7647 |
94
+ | 0.1447 | 24.96 | 156 | 0.7415 | 0.7255 |
95
+ | 0.1537 | 25.92 | 162 | 0.6668 | 0.7843 |
96
+ | 0.1537 | 26.88 | 168 | 0.7188 | 0.7451 |
97
+ | 0.1471 | 28.0 | 175 | 0.7291 | 0.7451 |
98
+ | 0.1241 | 28.96 | 181 | 0.5919 | 0.8039 |
99
+ | 0.1241 | 29.92 | 187 | 0.5211 | 0.8431 |
100
+ | 0.1058 | 30.88 | 193 | 0.6107 | 0.7843 |
101
+ | 0.1032 | 32.0 | 200 | 0.6863 | 0.7647 |
102
+ | 0.1032 | 32.96 | 206 | 0.6295 | 0.7647 |
103
+ | 0.1116 | 33.92 | 212 | 0.6061 | 0.7843 |
104
+ | 0.1116 | 34.88 | 218 | 0.6610 | 0.7843 |
105
+ | 0.0871 | 36.0 | 225 | 0.6109 | 0.8039 |
106
+ | 0.1037 | 36.96 | 231 | 0.6116 | 0.7843 |
107
+ | 0.1037 | 37.92 | 237 | 0.6176 | 0.8039 |
108
+ | 0.0802 | 38.4 | 240 | 0.6169 | 0.8039 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.36.2
114
+ - Pytorch 2.1.2+cu118
115
+ - Datasets 2.16.1
116
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7f9174542dde4bdb9f2b1ca0639ffa9a1dfee652f059a93422be754e49fb41c
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831dfd5dc2262f240342f9002011e543e1f63c23bfa5d7333f055ea65600ba89
3
  size 343230128
runs/Jun11_17-06-33_DESKTOP-SKBE9FB/events.out.tfevents.1718147195.DESKTOP-SKBE9FB.9452.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a80d3a88458ccce706cd91d9b32845cf23d45974b51ab79e21ca82d0989772
3
- size 12221
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcb84db5ed22269899260af57620e6847e0b8b984cedf068e0f53e9e766f1fe
3
+ size 21067