Hugging Face's logo

Augusto777
/
vit-base-patch16-224-ve-U12-b-80

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
21d19c7
•
1 Parent(s): 528e7f6

Model save

Browse files
Files changed (3) hide show
  1. README.md +151 -0
  2. model.safetensors +1 -1
  3. runs/Jun11_23-00-33_DESKTOP-SKBE9FB/events.out.tfevents.1718168434.DESKTOP-SKBE9FB.15616.0 +2 -2
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-U12-b-80
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: 0.8260869565217391
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-U12-b-80
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: 0.8850
36
+ - Accuracy: 0.8261
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: 80
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.92 | 6 | 1.3850 | 0.3478 |
71
+ | 1.3848 | 2.0 | 13 | 1.3701 | 0.4783 |
72
+ | 1.3848 | 2.92 | 19 | 1.3196 | 0.5 |
73
+ | 1.3508 | 4.0 | 26 | 1.2287 | 0.4130 |
74
+ | 1.2282 | 4.92 | 32 | 1.1280 | 0.3913 |
75
+ | 1.2282 | 6.0 | 39 | 1.0625 | 0.3913 |
76
+ | 1.0677 | 6.92 | 45 | 0.9840 | 0.5 |
77
+ | 0.9278 | 8.0 | 52 | 0.8970 | 0.6957 |
78
+ | 0.9278 | 8.92 | 58 | 0.8530 | 0.7391 |
79
+ | 0.8003 | 10.0 | 65 | 0.7872 | 0.8043 |
80
+ | 0.6486 | 10.92 | 71 | 0.6974 | 0.8043 |
81
+ | 0.6486 | 12.0 | 78 | 0.6409 | 0.8043 |
82
+ | 0.514 | 12.92 | 84 | 0.6050 | 0.8261 |
83
+ | 0.3945 | 14.0 | 91 | 0.6589 | 0.7609 |
84
+ | 0.3945 | 14.92 | 97 | 0.6343 | 0.7609 |
85
+ | 0.337 | 16.0 | 104 | 0.7340 | 0.7174 |
86
+ | 0.2779 | 16.92 | 110 | 0.5629 | 0.8261 |
87
+ | 0.2779 | 18.0 | 117 | 0.5934 | 0.8261 |
88
+ | 0.2374 | 18.92 | 123 | 0.7080 | 0.7609 |
89
+ | 0.2201 | 20.0 | 130 | 0.7100 | 0.7391 |
90
+ | 0.2201 | 20.92 | 136 | 0.7673 | 0.7609 |
91
+ | 0.1889 | 22.0 | 143 | 0.7889 | 0.7391 |
92
+ | 0.1889 | 22.92 | 149 | 0.7971 | 0.7391 |
93
+ | 0.1463 | 24.0 | 156 | 0.6888 | 0.7826 |
94
+ | 0.1261 | 24.92 | 162 | 0.8399 | 0.7609 |
95
+ | 0.1261 | 26.0 | 169 | 0.7244 | 0.7826 |
96
+ | 0.1489 | 26.92 | 175 | 0.8311 | 0.7391 |
97
+ | 0.1132 | 28.0 | 182 | 0.7987 | 0.7609 |
98
+ | 0.1132 | 28.92 | 188 | 0.7380 | 0.8043 |
99
+ | 0.1279 | 30.0 | 195 | 0.8103 | 0.8043 |
100
+ | 0.0925 | 30.92 | 201 | 0.8462 | 0.7609 |
101
+ | 0.0925 | 32.0 | 208 | 0.8233 | 0.8043 |
102
+ | 0.0893 | 32.92 | 214 | 0.8241 | 0.7826 |
103
+ | 0.083 | 34.0 | 221 | 0.8443 | 0.7826 |
104
+ | 0.083 | 34.92 | 227 | 0.8429 | 0.7826 |
105
+ | 0.1044 | 36.0 | 234 | 0.9362 | 0.7609 |
106
+ | 0.0739 | 36.92 | 240 | 1.1173 | 0.7391 |
107
+ | 0.0739 | 38.0 | 247 | 0.7812 | 0.8261 |
108
+ | 0.0962 | 38.92 | 253 | 0.7595 | 0.8043 |
109
+ | 0.0869 | 40.0 | 260 | 0.8031 | 0.8261 |
110
+ | 0.0869 | 40.92 | 266 | 0.8359 | 0.8261 |
111
+ | 0.0837 | 42.0 | 273 | 0.8151 | 0.8261 |
112
+ | 0.0837 | 42.92 | 279 | 0.8295 | 0.8261 |
113
+ | 0.0535 | 44.0 | 286 | 0.8096 | 0.8261 |
114
+ | 0.0694 | 44.92 | 292 | 0.8352 | 0.8261 |
115
+ | 0.0694 | 46.0 | 299 | 0.8216 | 0.8261 |
116
+ | 0.0736 | 46.92 | 305 | 0.8683 | 0.8043 |
117
+ | 0.0705 | 48.0 | 312 | 0.8554 | 0.8261 |
118
+ | 0.0705 | 48.92 | 318 | 0.8139 | 0.8478 |
119
+ | 0.0559 | 50.0 | 325 | 0.9030 | 0.7826 |
120
+ | 0.0474 | 50.92 | 331 | 0.9053 | 0.7609 |
121
+ | 0.0474 | 52.0 | 338 | 0.8810 | 0.8261 |
122
+ | 0.0477 | 52.92 | 344 | 0.8912 | 0.8043 |
123
+ | 0.0529 | 54.0 | 351 | 0.9078 | 0.8043 |
124
+ | 0.0529 | 54.92 | 357 | 0.8804 | 0.8043 |
125
+ | 0.038 | 56.0 | 364 | 0.9498 | 0.7826 |
126
+ | 0.0407 | 56.92 | 370 | 0.9134 | 0.8043 |
127
+ | 0.0407 | 58.0 | 377 | 0.8452 | 0.8478 |
128
+ | 0.0353 | 58.92 | 383 | 0.8735 | 0.8261 |
129
+ | 0.0349 | 60.0 | 390 | 0.9153 | 0.8043 |
130
+ | 0.0349 | 60.92 | 396 | 0.9209 | 0.8043 |
131
+ | 0.0322 | 62.0 | 403 | 0.9091 | 0.8261 |
132
+ | 0.0322 | 62.92 | 409 | 0.9137 | 0.8261 |
133
+ | 0.0392 | 64.0 | 416 | 0.8896 | 0.8261 |
134
+ | 0.0419 | 64.92 | 422 | 0.8613 | 0.8478 |
135
+ | 0.0419 | 66.0 | 429 | 0.8844 | 0.8261 |
136
+ | 0.0518 | 66.92 | 435 | 0.9093 | 0.8043 |
137
+ | 0.0349 | 68.0 | 442 | 0.9082 | 0.8043 |
138
+ | 0.0349 | 68.92 | 448 | 0.8879 | 0.8261 |
139
+ | 0.0359 | 70.0 | 455 | 0.8809 | 0.8261 |
140
+ | 0.0377 | 70.92 | 461 | 0.8777 | 0.8261 |
141
+ | 0.0377 | 72.0 | 468 | 0.8845 | 0.8261 |
142
+ | 0.0324 | 72.92 | 474 | 0.8845 | 0.8261 |
143
+ | 0.0365 | 73.85 | 480 | 0.8850 | 0.8261 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - Transformers 4.36.2
149
+ - Pytorch 2.1.2+cu118
150
+ - Datasets 2.16.1
151
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9296ca6deec292424d7b8bbf309d8c243e7fdabe7dd99c55cc6fefd040b5e4a
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0a99fba4cb3048815715ff9bf92f99ca434f0cca3669ef514df9ab4c293ada
3
  size 343230128
runs/Jun11_23-00-33_DESKTOP-SKBE9FB/events.out.tfevents.1718168434.DESKTOP-SKBE9FB.15616.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3245515d0a46facc230e77a47032e1f487360fbac7205993cdf47f0349ff9c51
3
- size 34029
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54f8636c73d591bd83aab28448c246944e93cb1d1a47d2bf77f40b8c6b79b02
3
+ size 36146