Hugging Face's logo

BilalMuftuoglu
/
beit-base-patch16-224-75-fold3

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
b60f712
•
1 Parent(s): 8b74e24

Model save

Browse files
Files changed (3) hide show
  1. README.md +177 -0
  2. model.safetensors +1 -1
  3. runs/May20_18-16-45_b94dbfcd7693/events.out.tfevents.1716229006.b94dbfcd7693.1289.23 +2 -2
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-patch16-224-75-fold3
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: 0.9534883720930233
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-patch16-224-75-fold3
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: 0.3298
36
+ - Accuracy: 0.9535
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 | 1.0 | 2 | 0.5223 | 0.8140 |
71
+ | No log | 2.0 | 4 | 0.5171 | 0.7907 |
72
+ | No log | 3.0 | 6 | 0.5562 | 0.7907 |
73
+ | No log | 4.0 | 8 | 0.5032 | 0.7907 |
74
+ | 0.5026 | 5.0 | 10 | 0.4636 | 0.7907 |
75
+ | 0.5026 | 6.0 | 12 | 0.4143 | 0.8372 |
76
+ | 0.5026 | 7.0 | 14 | 0.4338 | 0.8372 |
77
+ | 0.5026 | 8.0 | 16 | 0.4471 | 0.8372 |
78
+ | 0.5026 | 9.0 | 18 | 0.3882 | 0.8140 |
79
+ | 0.3578 | 10.0 | 20 | 0.3487 | 0.8372 |
80
+ | 0.3578 | 11.0 | 22 | 0.3975 | 0.8372 |
81
+ | 0.3578 | 12.0 | 24 | 0.3497 | 0.8372 |
82
+ | 0.3578 | 13.0 | 26 | 0.4257 | 0.8372 |
83
+ | 0.3578 | 14.0 | 28 | 0.2964 | 0.8837 |
84
+ | 0.322 | 15.0 | 30 | 0.4666 | 0.8372 |
85
+ | 0.322 | 16.0 | 32 | 0.3815 | 0.7907 |
86
+ | 0.322 | 17.0 | 34 | 0.2859 | 0.8837 |
87
+ | 0.322 | 18.0 | 36 | 0.5995 | 0.8140 |
88
+ | 0.322 | 19.0 | 38 | 0.4421 | 0.8372 |
89
+ | 0.2983 | 20.0 | 40 | 0.2857 | 0.9070 |
90
+ | 0.2983 | 21.0 | 42 | 0.3963 | 0.8605 |
91
+ | 0.2983 | 22.0 | 44 | 0.2775 | 0.9302 |
92
+ | 0.2983 | 23.0 | 46 | 0.4763 | 0.7442 |
93
+ | 0.2983 | 24.0 | 48 | 0.2789 | 0.8605 |
94
+ | 0.2545 | 25.0 | 50 | 0.3596 | 0.8372 |
95
+ | 0.2545 | 26.0 | 52 | 0.2447 | 0.9302 |
96
+ | 0.2545 | 27.0 | 54 | 0.4725 | 0.8140 |
97
+ | 0.2545 | 28.0 | 56 | 0.3389 | 0.8837 |
98
+ | 0.2545 | 29.0 | 58 | 0.3472 | 0.8140 |
99
+ | 0.1914 | 30.0 | 60 | 0.3326 | 0.9535 |
100
+ | 0.1914 | 31.0 | 62 | 0.2856 | 0.9302 |
101
+ | 0.1914 | 32.0 | 64 | 0.2857 | 0.8605 |
102
+ | 0.1914 | 33.0 | 66 | 0.2460 | 0.9302 |
103
+ | 0.1914 | 34.0 | 68 | 0.5097 | 0.8140 |
104
+ | 0.1782 | 35.0 | 70 | 0.2503 | 0.9535 |
105
+ | 0.1782 | 36.0 | 72 | 0.2338 | 0.9302 |
106
+ | 0.1782 | 37.0 | 74 | 0.4161 | 0.8837 |
107
+ | 0.1782 | 38.0 | 76 | 0.3522 | 0.9070 |
108
+ | 0.1782 | 39.0 | 78 | 0.2566 | 0.8372 |
109
+ | 0.1435 | 40.0 | 80 | 0.2658 | 0.8605 |
110
+ | 0.1435 | 41.0 | 82 | 0.2197 | 0.9302 |
111
+ | 0.1435 | 42.0 | 84 | 0.2200 | 0.8837 |
112
+ | 0.1435 | 43.0 | 86 | 0.2167 | 0.8837 |
113
+ | 0.1435 | 44.0 | 88 | 0.3905 | 0.9070 |
114
+ | 0.1131 | 45.0 | 90 | 0.5501 | 0.8837 |
115
+ | 0.1131 | 46.0 | 92 | 0.5251 | 0.9070 |
116
+ | 0.1131 | 47.0 | 94 | 0.4207 | 0.9070 |
117
+ | 0.1131 | 48.0 | 96 | 0.3181 | 0.8605 |
118
+ | 0.1131 | 49.0 | 98 | 0.4059 | 0.8140 |
119
+ | 0.1397 | 50.0 | 100 | 0.3061 | 0.8605 |
120
+ | 0.1397 | 51.0 | 102 | 0.2825 | 0.9302 |
121
+ | 0.1397 | 52.0 | 104 | 0.2886 | 0.9302 |
122
+ | 0.1397 | 53.0 | 106 | 0.3140 | 0.9070 |
123
+ | 0.1397 | 54.0 | 108 | 0.3363 | 0.9070 |
124
+ | 0.1048 | 55.0 | 110 | 0.3388 | 0.8837 |
125
+ | 0.1048 | 56.0 | 112 | 0.3391 | 0.9070 |
126
+ | 0.1048 | 57.0 | 114 | 0.3927 | 0.8605 |
127
+ | 0.1048 | 58.0 | 116 | 0.3799 | 0.8837 |
128
+ | 0.1048 | 59.0 | 118 | 0.5491 | 0.8140 |
129
+ | 0.1013 | 60.0 | 120 | 0.6218 | 0.8140 |
130
+ | 0.1013 | 61.0 | 122 | 0.4467 | 0.8372 |
131
+ | 0.1013 | 62.0 | 124 | 0.3842 | 0.9302 |
132
+ | 0.1013 | 63.0 | 126 | 0.3517 | 0.9302 |
133
+ | 0.1013 | 64.0 | 128 | 0.3083 | 0.9070 |
134
+ | 0.0987 | 65.0 | 130 | 0.3125 | 0.9535 |
135
+ | 0.0987 | 66.0 | 132 | 0.3968 | 0.9070 |
136
+ | 0.0987 | 67.0 | 134 | 0.3974 | 0.9070 |
137
+ | 0.0987 | 68.0 | 136 | 0.3304 | 0.9302 |
138
+ | 0.0987 | 69.0 | 138 | 0.3508 | 0.9070 |
139
+ | 0.0932 | 70.0 | 140 | 0.3760 | 0.9070 |
140
+ | 0.0932 | 71.0 | 142 | 0.3828 | 0.9535 |
141
+ | 0.0932 | 72.0 | 144 | 0.3291 | 0.9302 |
142
+ | 0.0932 | 73.0 | 146 | 0.3109 | 0.8837 |
143
+ | 0.0932 | 74.0 | 148 | 0.3078 | 0.9302 |
144
+ | 0.0917 | 75.0 | 150 | 0.4478 | 0.9070 |
145
+ | 0.0917 | 76.0 | 152 | 0.6594 | 0.8605 |
146
+ | 0.0917 | 77.0 | 154 | 0.6036 | 0.8605 |
147
+ | 0.0917 | 78.0 | 156 | 0.3920 | 0.9070 |
148
+ | 0.0917 | 79.0 | 158 | 0.3263 | 0.8605 |
149
+ | 0.0917 | 80.0 | 160 | 0.3551 | 0.8372 |
150
+ | 0.0917 | 81.0 | 162 | 0.3475 | 0.8372 |
151
+ | 0.0917 | 82.0 | 164 | 0.3338 | 0.8837 |
152
+ | 0.0917 | 83.0 | 166 | 0.3354 | 0.9070 |
153
+ | 0.0917 | 84.0 | 168 | 0.3611 | 0.9070 |
154
+ | 0.0901 | 85.0 | 170 | 0.3558 | 0.9070 |
155
+ | 0.0901 | 86.0 | 172 | 0.3412 | 0.8837 |
156
+ | 0.0901 | 87.0 | 174 | 0.3352 | 0.9302 |
157
+ | 0.0901 | 88.0 | 176 | 0.3627 | 0.9070 |
158
+ | 0.0901 | 89.0 | 178 | 0.3637 | 0.9070 |
159
+ | 0.0764 | 90.0 | 180 | 0.3369 | 0.9070 |
160
+ | 0.0764 | 91.0 | 182 | 0.3246 | 0.9302 |
161
+ | 0.0764 | 92.0 | 184 | 0.3208 | 0.9302 |
162
+ | 0.0764 | 93.0 | 186 | 0.3229 | 0.9302 |
163
+ | 0.0764 | 94.0 | 188 | 0.3326 | 0.9302 |
164
+ | 0.0664 | 95.0 | 190 | 0.3340 | 0.9302 |
165
+ | 0.0664 | 96.0 | 192 | 0.3296 | 0.9302 |
166
+ | 0.0664 | 97.0 | 194 | 0.3268 | 0.9302 |
167
+ | 0.0664 | 98.0 | 196 | 0.3260 | 0.9535 |
168
+ | 0.0664 | 99.0 | 198 | 0.3288 | 0.9535 |
169
+ | 0.057 | 100.0 | 200 | 0.3298 | 0.9535 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.40.2
175
+ - Pytorch 2.2.1+cu121
176
+ - Datasets 2.19.1
177
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36fa5f8a60baf43836d6121d8e8a6f521fb3f1156f2557bb294f7eb097d758ff
3
  size 343080328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3605c18a8f207e9554a052d4a648331880a7769630cc6b172c233edab4c44b59
3
  size 343080328
runs/May20_18-16-45_b94dbfcd7693/events.out.tfevents.1716229006.b94dbfcd7693.1289.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:657f646a30d54f48dd6211e66500dbbb11e9fd451735773067328c271a6f9721
3
- size 41636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25dd5155e081481fb6cead65efad12d9fca9c90fc653aa23e347b8ebc091b2a0
3
+ size 41990