Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-55-fold3

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
1951cac
·
verified ·
1 Parent(s): cddb707

Model save

Browse files
Files changed (3) hide show
  1. README.md +163 -0
  2. model.safetensors +1 -1
  3. runs/May21_20-41-57_804716d6a90a/events.out.tfevents.1716324118.804716d6a90a.958.4 +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-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: 0.7848101265822784
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-fold3
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: 0.8731
36
+ - Accuracy: 0.7848
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 | 0.8367 | 0.4051 |
71
+ | No log | 2.0 | 7 | 0.7223 | 0.4557 |
72
+ | 0.7025 | 2.8571 | 10 | 0.7199 | 0.4684 |
73
+ | 0.7025 | 4.0 | 14 | 0.6096 | 0.7089 |
74
+ | 0.7025 | 4.8571 | 17 | 0.6278 | 0.5823 |
75
+ | 0.6356 | 6.0 | 21 | 0.5629 | 0.7089 |
76
+ | 0.6356 | 6.8571 | 24 | 0.5924 | 0.6835 |
77
+ | 0.6356 | 8.0 | 28 | 0.5365 | 0.7722 |
78
+ | 0.5493 | 8.8571 | 31 | 0.6082 | 0.6329 |
79
+ | 0.5493 | 10.0 | 35 | 0.7239 | 0.5949 |
80
+ | 0.5493 | 10.8571 | 38 | 0.5435 | 0.7722 |
81
+ | 0.5205 | 12.0 | 42 | 0.8530 | 0.5570 |
82
+ | 0.5205 | 12.8571 | 45 | 0.5530 | 0.6709 |
83
+ | 0.5205 | 14.0 | 49 | 0.4728 | 0.7722 |
84
+ | 0.4979 | 14.8571 | 52 | 0.9571 | 0.5570 |
85
+ | 0.4979 | 16.0 | 56 | 0.5193 | 0.7722 |
86
+ | 0.4979 | 16.8571 | 59 | 0.4529 | 0.8228 |
87
+ | 0.4957 | 18.0 | 63 | 0.4686 | 0.7975 |
88
+ | 0.4957 | 18.8571 | 66 | 0.5060 | 0.7722 |
89
+ | 0.3659 | 20.0 | 70 | 0.4821 | 0.7848 |
90
+ | 0.3659 | 20.8571 | 73 | 0.6116 | 0.7089 |
91
+ | 0.3659 | 22.0 | 77 | 0.5860 | 0.7215 |
92
+ | 0.2973 | 22.8571 | 80 | 0.7100 | 0.7089 |
93
+ | 0.2973 | 24.0 | 84 | 0.6446 | 0.7342 |
94
+ | 0.2973 | 24.8571 | 87 | 0.6294 | 0.7342 |
95
+ | 0.2647 | 26.0 | 91 | 0.5988 | 0.7342 |
96
+ | 0.2647 | 26.8571 | 94 | 0.5256 | 0.7342 |
97
+ | 0.2647 | 28.0 | 98 | 0.6628 | 0.7595 |
98
+ | 0.2527 | 28.8571 | 101 | 0.5054 | 0.7595 |
99
+ | 0.2527 | 30.0 | 105 | 0.7632 | 0.7595 |
100
+ | 0.2527 | 30.8571 | 108 | 0.5917 | 0.7848 |
101
+ | 0.2176 | 32.0 | 112 | 0.5293 | 0.7848 |
102
+ | 0.2176 | 32.8571 | 115 | 0.6048 | 0.7468 |
103
+ | 0.2176 | 34.0 | 119 | 0.5710 | 0.7468 |
104
+ | 0.1633 | 34.8571 | 122 | 0.5901 | 0.7595 |
105
+ | 0.1633 | 36.0 | 126 | 0.8161 | 0.7468 |
106
+ | 0.1633 | 36.8571 | 129 | 0.7202 | 0.7468 |
107
+ | 0.1753 | 38.0 | 133 | 0.8239 | 0.7215 |
108
+ | 0.1753 | 38.8571 | 136 | 0.8908 | 0.7215 |
109
+ | 0.1743 | 40.0 | 140 | 0.8519 | 0.7342 |
110
+ | 0.1743 | 40.8571 | 143 | 1.0071 | 0.7215 |
111
+ | 0.1743 | 42.0 | 147 | 0.7842 | 0.7342 |
112
+ | 0.1532 | 42.8571 | 150 | 0.7827 | 0.7089 |
113
+ | 0.1532 | 44.0 | 154 | 0.7150 | 0.7468 |
114
+ | 0.1532 | 44.8571 | 157 | 0.6905 | 0.7595 |
115
+ | 0.1526 | 46.0 | 161 | 0.9260 | 0.7089 |
116
+ | 0.1526 | 46.8571 | 164 | 0.7933 | 0.7595 |
117
+ | 0.1526 | 48.0 | 168 | 0.8580 | 0.7468 |
118
+ | 0.1519 | 48.8571 | 171 | 0.6899 | 0.7975 |
119
+ | 0.1519 | 50.0 | 175 | 0.7069 | 0.7848 |
120
+ | 0.1519 | 50.8571 | 178 | 0.6741 | 0.7595 |
121
+ | 0.1292 | 52.0 | 182 | 0.7183 | 0.7848 |
122
+ | 0.1292 | 52.8571 | 185 | 0.8051 | 0.7468 |
123
+ | 0.1292 | 54.0 | 189 | 0.6883 | 0.7722 |
124
+ | 0.1305 | 54.8571 | 192 | 0.8266 | 0.7468 |
125
+ | 0.1305 | 56.0 | 196 | 1.0871 | 0.7595 |
126
+ | 0.1305 | 56.8571 | 199 | 0.7595 | 0.7595 |
127
+ | 0.1129 | 58.0 | 203 | 0.6880 | 0.7595 |
128
+ | 0.1129 | 58.8571 | 206 | 1.0676 | 0.7595 |
129
+ | 0.1369 | 60.0 | 210 | 0.8078 | 0.7595 |
130
+ | 0.1369 | 60.8571 | 213 | 0.7850 | 0.7595 |
131
+ | 0.1369 | 62.0 | 217 | 0.6975 | 0.7722 |
132
+ | 0.127 | 62.8571 | 220 | 0.7212 | 0.7595 |
133
+ | 0.127 | 64.0 | 224 | 0.8967 | 0.7468 |
134
+ | 0.127 | 64.8571 | 227 | 1.0046 | 0.7595 |
135
+ | 0.1238 | 66.0 | 231 | 0.8611 | 0.7342 |
136
+ | 0.1238 | 66.8571 | 234 | 0.9676 | 0.7975 |
137
+ | 0.1238 | 68.0 | 238 | 1.3115 | 0.7215 |
138
+ | 0.1068 | 68.8571 | 241 | 1.0992 | 0.7468 |
139
+ | 0.1068 | 70.0 | 245 | 0.8765 | 0.7848 |
140
+ | 0.1068 | 70.8571 | 248 | 0.8510 | 0.7848 |
141
+ | 0.1019 | 72.0 | 252 | 0.7403 | 0.7975 |
142
+ | 0.1019 | 72.8571 | 255 | 0.7459 | 0.7975 |
143
+ | 0.1019 | 74.0 | 259 | 0.7705 | 0.7975 |
144
+ | 0.1002 | 74.8571 | 262 | 0.7535 | 0.7975 |
145
+ | 0.1002 | 76.0 | 266 | 0.7124 | 0.7722 |
146
+ | 0.1002 | 76.8571 | 269 | 0.7014 | 0.7342 |
147
+ | 0.1222 | 78.0 | 273 | 0.8068 | 0.7722 |
148
+ | 0.1222 | 78.8571 | 276 | 0.9451 | 0.7722 |
149
+ | 0.1091 | 80.0 | 280 | 1.0048 | 0.7848 |
150
+ | 0.1091 | 80.8571 | 283 | 0.9518 | 0.7722 |
151
+ | 0.1091 | 82.0 | 287 | 0.8575 | 0.7848 |
152
+ | 0.0957 | 82.8571 | 290 | 0.8441 | 0.7848 |
153
+ | 0.0957 | 84.0 | 294 | 0.8602 | 0.7848 |
154
+ | 0.0957 | 84.8571 | 297 | 0.8701 | 0.7848 |
155
+ | 0.1111 | 85.7143 | 300 | 0.8731 | 0.7848 |
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 sha256:2ae5590c9ab8cab612d36ad851b25c99e5fdc749ab2fee71778815aa0e63dc20
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1becda5c0a78af98081986bfc2191bdc83c2f887646d52ecfeb84eb73c89321e
3
  size 343230408
runs/May21_20-41-57_804716d6a90a/events.out.tfevents.1716324118.804716d6a90a.958.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:131ed424b2cfb4ba43d7061e0f7488695497f71601134f41e1f4bda1066b9e43
3
- size 38755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9581d40e68346af4230e817fe4ca4a4ddb2c74dadad1939264109c1206843d61
3
+ size 39109