Hugging Face's logo

BilalMuftuoglu
/
beit-base-patch16-224-65-fold4

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
c73eab5
•
1 Parent(s): 28e6366

Model save

Browse files
Files changed (3) hide show
  1. README.md +170 -0
  2. model.safetensors +1 -1
  3. runs/May20_16-33-45_b94dbfcd7693/events.out.tfevents.1716222826.b94dbfcd7693.1289.15 +2 -2
README.md ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: beit-base-patch16-224-65-fold4
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8028169014084507
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
+ # beit-base-patch16-224-65-fold4
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8469
36
+ - Accuracy: 0.8028
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: 100
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | No log | 0.9231 | 3 | 0.7415 | 0.5352 |
71
+ | No log | 1.8462 | 6 | 0.7177 | 0.4507 |
72
+ | No log | 2.7692 | 9 | 0.6709 | 0.6056 |
73
+ | 0.748 | 4.0 | 13 | 0.6333 | 0.6338 |
74
+ | 0.748 | 4.9231 | 16 | 0.6162 | 0.7324 |
75
+ | 0.748 | 5.8462 | 19 | 0.6303 | 0.6338 |
76
+ | 0.6397 | 6.7692 | 22 | 0.5950 | 0.6761 |
77
+ | 0.6397 | 8.0 | 26 | 0.6325 | 0.6056 |
78
+ | 0.6397 | 8.9231 | 29 | 0.5799 | 0.7042 |
79
+ | 0.5957 | 9.8462 | 32 | 0.5793 | 0.6901 |
80
+ | 0.5957 | 10.7692 | 35 | 0.5869 | 0.7183 |
81
+ | 0.5957 | 12.0 | 39 | 0.6195 | 0.5775 |
82
+ | 0.5676 | 12.9231 | 42 | 0.5940 | 0.6479 |
83
+ | 0.5676 | 13.8462 | 45 | 0.6612 | 0.6197 |
84
+ | 0.5676 | 14.7692 | 48 | 0.5598 | 0.7465 |
85
+ | 0.5952 | 16.0 | 52 | 0.5472 | 0.7465 |
86
+ | 0.5952 | 16.9231 | 55 | 0.4823 | 0.7887 |
87
+ | 0.5952 | 17.8462 | 58 | 0.6493 | 0.6901 |
88
+ | 0.4908 | 18.7692 | 61 | 0.5539 | 0.7465 |
89
+ | 0.4908 | 20.0 | 65 | 0.5406 | 0.7606 |
90
+ | 0.4908 | 20.9231 | 68 | 0.5443 | 0.7606 |
91
+ | 0.4474 | 21.8462 | 71 | 0.6548 | 0.7042 |
92
+ | 0.4474 | 22.7692 | 74 | 0.4924 | 0.7746 |
93
+ | 0.4474 | 24.0 | 78 | 0.4671 | 0.8169 |
94
+ | 0.4106 | 24.9231 | 81 | 0.4117 | 0.8310 |
95
+ | 0.4106 | 25.8462 | 84 | 0.4630 | 0.8592 |
96
+ | 0.4106 | 26.7692 | 87 | 0.4915 | 0.8310 |
97
+ | 0.3163 | 28.0 | 91 | 0.6336 | 0.8028 |
98
+ | 0.3163 | 28.9231 | 94 | 0.5920 | 0.7887 |
99
+ | 0.3163 | 29.8462 | 97 | 0.5653 | 0.8028 |
100
+ | 0.3234 | 30.7692 | 100 | 0.6411 | 0.7746 |
101
+ | 0.3234 | 32.0 | 104 | 0.6728 | 0.7887 |
102
+ | 0.3234 | 32.9231 | 107 | 0.5503 | 0.8028 |
103
+ | 0.2969 | 33.8462 | 110 | 0.4914 | 0.8310 |
104
+ | 0.2969 | 34.7692 | 113 | 0.5952 | 0.8169 |
105
+ | 0.2969 | 36.0 | 117 | 0.7161 | 0.7746 |
106
+ | 0.2325 | 36.9231 | 120 | 0.6517 | 0.7746 |
107
+ | 0.2325 | 37.8462 | 123 | 0.5832 | 0.7887 |
108
+ | 0.2325 | 38.7692 | 126 | 0.6309 | 0.7746 |
109
+ | 0.2447 | 40.0 | 130 | 0.8011 | 0.7465 |
110
+ | 0.2447 | 40.9231 | 133 | 0.6085 | 0.7887 |
111
+ | 0.2447 | 41.8462 | 136 | 0.6470 | 0.7606 |
112
+ | 0.2447 | 42.7692 | 139 | 0.7744 | 0.7746 |
113
+ | 0.2217 | 44.0 | 143 | 0.5730 | 0.8310 |
114
+ | 0.2217 | 44.9231 | 146 | 0.5577 | 0.8169 |
115
+ | 0.2217 | 45.8462 | 149 | 0.5226 | 0.8451 |
116
+ | 0.2231 | 46.7692 | 152 | 0.5115 | 0.8310 |
117
+ | 0.2231 | 48.0 | 156 | 0.5415 | 0.8732 |
118
+ | 0.2231 | 48.9231 | 159 | 0.5971 | 0.8310 |
119
+ | 0.2014 | 49.8462 | 162 | 0.8717 | 0.7606 |
120
+ | 0.2014 | 50.7692 | 165 | 0.7063 | 0.7887 |
121
+ | 0.2014 | 52.0 | 169 | 0.6917 | 0.7887 |
122
+ | 0.1827 | 52.9231 | 172 | 0.6880 | 0.7887 |
123
+ | 0.1827 | 53.8462 | 175 | 0.7027 | 0.8028 |
124
+ | 0.1827 | 54.7692 | 178 | 0.6764 | 0.8310 |
125
+ | 0.1558 | 56.0 | 182 | 0.7398 | 0.7887 |
126
+ | 0.1558 | 56.9231 | 185 | 0.7787 | 0.8169 |
127
+ | 0.1558 | 57.8462 | 188 | 0.7678 | 0.8169 |
128
+ | 0.1637 | 58.7692 | 191 | 0.7898 | 0.7606 |
129
+ | 0.1637 | 60.0 | 195 | 0.7105 | 0.8310 |
130
+ | 0.1637 | 60.9231 | 198 | 0.7262 | 0.8592 |
131
+ | 0.1591 | 61.8462 | 201 | 0.7464 | 0.8169 |
132
+ | 0.1591 | 62.7692 | 204 | 0.7233 | 0.8310 |
133
+ | 0.1591 | 64.0 | 208 | 0.7263 | 0.8310 |
134
+ | 0.1521 | 64.9231 | 211 | 0.7377 | 0.8028 |
135
+ | 0.1521 | 65.8462 | 214 | 0.7267 | 0.8310 |
136
+ | 0.1521 | 66.7692 | 217 | 0.7178 | 0.8169 |
137
+ | 0.157 | 68.0 | 221 | 0.8585 | 0.7887 |
138
+ | 0.157 | 68.9231 | 224 | 0.8629 | 0.7887 |
139
+ | 0.157 | 69.8462 | 227 | 0.7329 | 0.8028 |
140
+ | 0.1593 | 70.7692 | 230 | 0.6997 | 0.8310 |
141
+ | 0.1593 | 72.0 | 234 | 0.8074 | 0.8028 |
142
+ | 0.1593 | 72.9231 | 237 | 1.0352 | 0.7887 |
143
+ | 0.134 | 73.8462 | 240 | 1.0472 | 0.7887 |
144
+ | 0.134 | 74.7692 | 243 | 0.7477 | 0.8169 |
145
+ | 0.134 | 76.0 | 247 | 0.7357 | 0.8310 |
146
+ | 0.1386 | 76.9231 | 250 | 0.8497 | 0.7887 |
147
+ | 0.1386 | 77.8462 | 253 | 0.9464 | 0.7746 |
148
+ | 0.1386 | 78.7692 | 256 | 0.8535 | 0.7887 |
149
+ | 0.1246 | 80.0 | 260 | 0.7998 | 0.8310 |
150
+ | 0.1246 | 80.9231 | 263 | 0.8214 | 0.8310 |
151
+ | 0.1246 | 81.8462 | 266 | 0.8374 | 0.8028 |
152
+ | 0.1246 | 82.7692 | 269 | 0.8597 | 0.8028 |
153
+ | 0.1271 | 84.0 | 273 | 0.8437 | 0.8028 |
154
+ | 0.1271 | 84.9231 | 276 | 0.8370 | 0.8028 |
155
+ | 0.1271 | 85.8462 | 279 | 0.8298 | 0.8028 |
156
+ | 0.1274 | 86.7692 | 282 | 0.8340 | 0.8028 |
157
+ | 0.1274 | 88.0 | 286 | 0.8462 | 0.8028 |
158
+ | 0.1274 | 88.9231 | 289 | 0.8594 | 0.8028 |
159
+ | 0.1251 | 89.8462 | 292 | 0.8504 | 0.8028 |
160
+ | 0.1251 | 90.7692 | 295 | 0.8480 | 0.8028 |
161
+ | 0.1251 | 92.0 | 299 | 0.8471 | 0.8028 |
162
+ | 0.1207 | 92.3077 | 300 | 0.8469 | 0.8028 |
163
+
164
+
165
+ ### Framework versions
166
+
167
+ - Transformers 4.40.2
168
+ - Pytorch 2.2.1+cu121
169
+ - Datasets 2.19.1
170
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:168417097ab7225bdefd4775a8268f3a61e48674a3e7ab7d0c38e9218adb5563
3
  size 343080328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98da3b7a7b301e36abbf4ffcf8ffb6848fe415d96285c3ab82f55d3703918428
3
  size 343080328
runs/May20_16-33-45_b94dbfcd7693/events.out.tfevents.1716222826.b94dbfcd7693.1289.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:649145ec90a1404ca759f14bae452cf86de4c695d3050f8aaf9a5a555f49d019
3
- size 41095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7839e43f618006a0c102b6c1b904768d966decaa5daf88a1ee9be416841531e3
3
+ size 41983