Hugging Face's logo

Augusto777
/
vit-base-patch16-224-ve-Ub

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
7ae5f5b
•
1 Parent(s): a1ccc47

Model save

Browse files
Files changed (3) hide show
  1. README.md +123 -0
  2. model.safetensors +1 -1
  3. runs/Jun17_10-58-29_DESKTOP-SKBE9FB/events.out.tfevents.1718643510.DESKTOP-SKBE9FB.9632.0 +2 -2
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Ub
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: 0.7058823529411765
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-Ub
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: 0.8187
36
+ - Accuracy: 0.7059
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: 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: 0.1
64
+ - num_epochs: 80
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.57 | 1 | 1.3863 | 0.0980 |
71
+ | No log | 1.71 | 3 | 1.3813 | 0.4706 |
72
+ | No log | 2.86 | 5 | 1.3686 | 0.4706 |
73
+ | No log | 4.0 | 7 | 1.3480 | 0.4706 |
74
+ | No log | 4.57 | 8 | 1.3345 | 0.4706 |
75
+ | 1.3658 | 5.71 | 10 | 1.3040 | 0.4706 |
76
+ | 1.3658 | 6.86 | 12 | 1.2754 | 0.4706 |
77
+ | 1.3658 | 8.0 | 14 | 1.2477 | 0.4902 |
78
+ | 1.3658 | 8.57 | 15 | 1.2347 | 0.5294 |
79
+ | 1.3658 | 9.71 | 17 | 1.2109 | 0.5490 |
80
+ | 1.3658 | 10.86 | 19 | 1.1889 | 0.6078 |
81
+ | 1.2512 | 12.0 | 21 | 1.1671 | 0.6275 |
82
+ | 1.2512 | 12.57 | 22 | 1.1560 | 0.6078 |
83
+ | 1.2512 | 13.71 | 24 | 1.1311 | 0.6471 |
84
+ | 1.2512 | 14.86 | 26 | 1.1128 | 0.6275 |
85
+ | 1.2512 | 16.0 | 28 | 1.0874 | 0.6667 |
86
+ | 1.2512 | 16.57 | 29 | 1.0828 | 0.6863 |
87
+ | 1.1299 | 17.71 | 31 | 1.0586 | 0.6667 |
88
+ | 1.1299 | 18.86 | 33 | 1.0362 | 0.6667 |
89
+ | 1.1299 | 20.0 | 35 | 1.0173 | 0.6863 |
90
+ | 1.1299 | 20.57 | 36 | 1.0065 | 0.6667 |
91
+ | 1.1299 | 21.71 | 38 | 1.0070 | 0.6471 |
92
+ | 1.0212 | 22.86 | 40 | 0.9792 | 0.6667 |
93
+ | 1.0212 | 24.0 | 42 | 0.9612 | 0.6667 |
94
+ | 1.0212 | 24.57 | 43 | 0.9584 | 0.6471 |
95
+ | 1.0212 | 25.71 | 45 | 0.9494 | 0.6667 |
96
+ | 1.0212 | 26.86 | 47 | 0.9294 | 0.6667 |
97
+ | 1.0212 | 28.0 | 49 | 0.9196 | 0.6667 |
98
+ | 0.9222 | 28.57 | 50 | 0.9100 | 0.7059 |
99
+ | 0.9222 | 29.71 | 52 | 0.9061 | 0.6863 |
100
+ | 0.9222 | 30.86 | 54 | 0.8904 | 0.7059 |
101
+ | 0.9222 | 32.0 | 56 | 0.8797 | 0.7059 |
102
+ | 0.9222 | 32.57 | 57 | 0.8747 | 0.6863 |
103
+ | 0.9222 | 33.71 | 59 | 0.8691 | 0.6863 |
104
+ | 0.8419 | 34.86 | 61 | 0.8550 | 0.7059 |
105
+ | 0.8419 | 36.0 | 63 | 0.8470 | 0.7255 |
106
+ | 0.8419 | 36.57 | 64 | 0.8430 | 0.7255 |
107
+ | 0.8419 | 37.71 | 66 | 0.8389 | 0.7059 |
108
+ | 0.8419 | 38.86 | 68 | 0.8298 | 0.7255 |
109
+ | 0.7865 | 40.0 | 70 | 0.8270 | 0.7255 |
110
+ | 0.7865 | 40.57 | 71 | 0.8258 | 0.7255 |
111
+ | 0.7865 | 41.71 | 73 | 0.8235 | 0.7059 |
112
+ | 0.7865 | 42.86 | 75 | 0.8211 | 0.7059 |
113
+ | 0.7865 | 44.0 | 77 | 0.8189 | 0.7059 |
114
+ | 0.7865 | 44.57 | 78 | 0.8189 | 0.7059 |
115
+ | 0.7555 | 45.71 | 80 | 0.8187 | 0.7059 |
116
+
117
+
118
+ ### Framework versions
119
+
120
+ - Transformers 4.36.2
121
+ - Pytorch 2.1.2+cu118
122
+ - Datasets 2.16.1
123
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6f2985e0ec4d5e041a25ba657a5236809fabbd1a4fffa07c1071bb4f411ed35
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed31dc25ecb84fe1d0a31204d4a3af3a048d06f450db5c0737a91e9dde7a397e
3
  size 343230128
runs/Jun17_10-58-29_DESKTOP-SKBE9FB/events.out.tfevents.1718643510.DESKTOP-SKBE9FB.9632.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d89b144bc898632917fc0203b3d447f35df42d2659ef9a4f91bbfb22dfb6bc3
3
- size 20297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96235b9254e096a54541431f60929bb1e968e89c4e7e1e135ebff7c6d2e333e
3
+ size 20645