Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-55-fold4

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
be6e6ef
•
1 Parent(s): aad3dd9

Model save

Browse files
Files changed (3) hide show
  1. README.md +163 -0
  2. model.safetensors +1 -1
  3. runs/May21_21-09-57_804716d6a90a/events.out.tfevents.1716325797.804716d6a90a.958.6 +2 -2
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-base-distilled-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: deit-base-distilled-patch16-224-55-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: 0.810126582278481
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
+ # deit-base-distilled-patch16-224-55-fold4
32
+
33
+ This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8042
36
+ - Accuracy: 0.8101
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 | 0.8571 | 3 | 0.8297 | 0.5063 |
71
+ | No log | 2.0 | 7 | 0.6548 | 0.6203 |
72
+ | 0.6826 | 2.8571 | 10 | 0.6513 | 0.5190 |
73
+ | 0.6826 | 4.0 | 14 | 0.6024 | 0.7342 |
74
+ | 0.6826 | 4.8571 | 17 | 0.6473 | 0.5823 |
75
+ | 0.6198 | 6.0 | 21 | 0.5717 | 0.6835 |
76
+ | 0.6198 | 6.8571 | 24 | 0.7837 | 0.5570 |
77
+ | 0.6198 | 8.0 | 28 | 0.5272 | 0.7595 |
78
+ | 0.5409 | 8.8571 | 31 | 0.5162 | 0.7342 |
79
+ | 0.5409 | 10.0 | 35 | 0.6156 | 0.6709 |
80
+ | 0.5409 | 10.8571 | 38 | 0.5844 | 0.6582 |
81
+ | 0.5177 | 12.0 | 42 | 0.7013 | 0.6709 |
82
+ | 0.5177 | 12.8571 | 45 | 0.5017 | 0.7722 |
83
+ | 0.5177 | 14.0 | 49 | 0.4723 | 0.7975 |
84
+ | 0.4995 | 14.8571 | 52 | 0.7057 | 0.6835 |
85
+ | 0.4995 | 16.0 | 56 | 0.4669 | 0.8228 |
86
+ | 0.4995 | 16.8571 | 59 | 0.5737 | 0.7468 |
87
+ | 0.3767 | 18.0 | 63 | 0.5035 | 0.8101 |
88
+ | 0.3767 | 18.8571 | 66 | 0.8993 | 0.6203 |
89
+ | 0.3602 | 20.0 | 70 | 0.5425 | 0.7975 |
90
+ | 0.3602 | 20.8571 | 73 | 0.5605 | 0.7722 |
91
+ | 0.3602 | 22.0 | 77 | 0.4260 | 0.7975 |
92
+ | 0.3479 | 22.8571 | 80 | 0.4117 | 0.8228 |
93
+ | 0.3479 | 24.0 | 84 | 0.4017 | 0.7975 |
94
+ | 0.3479 | 24.8571 | 87 | 0.4401 | 0.8228 |
95
+ | 0.2845 | 26.0 | 91 | 0.4490 | 0.7975 |
96
+ | 0.2845 | 26.8571 | 94 | 0.5080 | 0.8101 |
97
+ | 0.2845 | 28.0 | 98 | 0.5014 | 0.7975 |
98
+ | 0.2316 | 28.8571 | 101 | 0.5385 | 0.7722 |
99
+ | 0.2316 | 30.0 | 105 | 0.5643 | 0.7595 |
100
+ | 0.2316 | 30.8571 | 108 | 0.4887 | 0.7848 |
101
+ | 0.2212 | 32.0 | 112 | 0.5253 | 0.7975 |
102
+ | 0.2212 | 32.8571 | 115 | 0.4633 | 0.7975 |
103
+ | 0.2212 | 34.0 | 119 | 0.5079 | 0.8228 |
104
+ | 0.2093 | 34.8571 | 122 | 0.5082 | 0.7975 |
105
+ | 0.2093 | 36.0 | 126 | 0.6113 | 0.7468 |
106
+ | 0.2093 | 36.8571 | 129 | 0.5094 | 0.7848 |
107
+ | 0.179 | 38.0 | 133 | 0.6253 | 0.8101 |
108
+ | 0.179 | 38.8571 | 136 | 0.5406 | 0.7848 |
109
+ | 0.173 | 40.0 | 140 | 0.6687 | 0.7722 |
110
+ | 0.173 | 40.8571 | 143 | 0.5691 | 0.7975 |
111
+ | 0.173 | 42.0 | 147 | 0.5776 | 0.7975 |
112
+ | 0.1881 | 42.8571 | 150 | 0.7816 | 0.7595 |
113
+ | 0.1881 | 44.0 | 154 | 0.4908 | 0.8354 |
114
+ | 0.1881 | 44.8571 | 157 | 0.5330 | 0.7848 |
115
+ | 0.161 | 46.0 | 161 | 0.5351 | 0.7848 |
116
+ | 0.161 | 46.8571 | 164 | 0.6663 | 0.7848 |
117
+ | 0.161 | 48.0 | 168 | 0.5382 | 0.7975 |
118
+ | 0.1446 | 48.8571 | 171 | 0.5877 | 0.7848 |
119
+ | 0.1446 | 50.0 | 175 | 0.6856 | 0.8228 |
120
+ | 0.1446 | 50.8571 | 178 | 0.6044 | 0.8101 |
121
+ | 0.1556 | 52.0 | 182 | 0.7954 | 0.7848 |
122
+ | 0.1556 | 52.8571 | 185 | 0.7432 | 0.7848 |
123
+ | 0.1556 | 54.0 | 189 | 0.7896 | 0.8101 |
124
+ | 0.1602 | 54.8571 | 192 | 0.8400 | 0.8101 |
125
+ | 0.1602 | 56.0 | 196 | 0.8243 | 0.7848 |
126
+ | 0.1602 | 56.8571 | 199 | 0.6864 | 0.8354 |
127
+ | 0.1357 | 58.0 | 203 | 0.7131 | 0.7722 |
128
+ | 0.1357 | 58.8571 | 206 | 0.9191 | 0.7722 |
129
+ | 0.1262 | 60.0 | 210 | 0.7465 | 0.7722 |
130
+ | 0.1262 | 60.8571 | 213 | 0.7127 | 0.7848 |
131
+ | 0.1262 | 62.0 | 217 | 0.6973 | 0.7975 |
132
+ | 0.1323 | 62.8571 | 220 | 0.7125 | 0.7848 |
133
+ | 0.1323 | 64.0 | 224 | 0.7235 | 0.7848 |
134
+ | 0.1323 | 64.8571 | 227 | 0.7200 | 0.7975 |
135
+ | 0.1258 | 66.0 | 231 | 0.7616 | 0.7848 |
136
+ | 0.1258 | 66.8571 | 234 | 0.8537 | 0.7848 |
137
+ | 0.1258 | 68.0 | 238 | 0.8223 | 0.7848 |
138
+ | 0.1316 | 68.8571 | 241 | 0.7751 | 0.8228 |
139
+ | 0.1316 | 70.0 | 245 | 0.7689 | 0.8228 |
140
+ | 0.1316 | 70.8571 | 248 | 0.7751 | 0.8101 |
141
+ | 0.1104 | 72.0 | 252 | 0.7770 | 0.8101 |
142
+ | 0.1104 | 72.8571 | 255 | 0.7916 | 0.7975 |
143
+ | 0.1104 | 74.0 | 259 | 0.7995 | 0.7848 |
144
+ | 0.1239 | 74.8571 | 262 | 0.7981 | 0.7848 |
145
+ | 0.1239 | 76.0 | 266 | 0.7890 | 0.8228 |
146
+ | 0.1239 | 76.8571 | 269 | 0.7888 | 0.8228 |
147
+ | 0.1057 | 78.0 | 273 | 0.7957 | 0.8228 |
148
+ | 0.1057 | 78.8571 | 276 | 0.7979 | 0.8228 |
149
+ | 0.1015 | 80.0 | 280 | 0.7959 | 0.8101 |
150
+ | 0.1015 | 80.8571 | 283 | 0.7935 | 0.8101 |
151
+ | 0.1015 | 82.0 | 287 | 0.7973 | 0.8228 |
152
+ | 0.101 | 82.8571 | 290 | 0.8033 | 0.7975 |
153
+ | 0.101 | 84.0 | 294 | 0.8072 | 0.7975 |
154
+ | 0.101 | 84.8571 | 297 | 0.8049 | 0.7975 |
155
+ | 0.1116 | 85.7143 | 300 | 0.8042 | 0.8101 |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - Transformers 4.41.0
161
+ - Pytorch 2.3.0+cu121
162
+ - Datasets 2.19.1
163
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:910ee8c08ac599ad158ea76dc53bf87d25a218566858eceaaed878c328adbcd6
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b3e9025222d8ea122b4ffbd1cee0d3fce2509a14ab56d54f6cc9c86f71718b
3
  size 343230408
runs/May21_21-09-57_804716d6a90a/events.out.tfevents.1716325797.804716d6a90a.958.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b7ebab33442000fb1578887e2d4910265e122e78245a1d6fd945329fccbb76c
3
- size 38755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f7728d5e0ecd4c294b3e7d96a0629a5ba3ec6caa71a22728baaa0f06246cbf
3
+ size 39109