Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-55-fold2

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
89674b0
·
verified ·
1 Parent(s): db4ca57

Model save

Browse files
Files changed (3) hide show
  1. README.md +163 -0
  2. model.safetensors +1 -1
  3. runs/May21_20-13-34_804716d6a90a/events.out.tfevents.1716322415.804716d6a90a.958.2 +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-fold2
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: 0.7468354430379747
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-fold2
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: 0.8551
36
+ - Accuracy: 0.7468
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 | 0.7763 | 0.5443 |
71
+ | No log | 2.0 | 7 | 0.6780 | 0.6203 |
72
+ | 0.721 | 2.8571 | 10 | 0.6954 | 0.5316 |
73
+ | 0.721 | 4.0 | 14 | 0.6370 | 0.6203 |
74
+ | 0.721 | 4.8571 | 17 | 0.6105 | 0.5949 |
75
+ | 0.6207 | 6.0 | 21 | 0.5798 | 0.6835 |
76
+ | 0.6207 | 6.8571 | 24 | 0.5704 | 0.7468 |
77
+ | 0.6207 | 8.0 | 28 | 0.5879 | 0.7089 |
78
+ | 0.5427 | 8.8571 | 31 | 0.6727 | 0.6582 |
79
+ | 0.5427 | 10.0 | 35 | 0.5841 | 0.6962 |
80
+ | 0.5427 | 10.8571 | 38 | 0.6059 | 0.6962 |
81
+ | 0.4775 | 12.0 | 42 | 1.0271 | 0.6076 |
82
+ | 0.4775 | 12.8571 | 45 | 0.6412 | 0.7089 |
83
+ | 0.4775 | 14.0 | 49 | 0.8064 | 0.6582 |
84
+ | 0.4961 | 14.8571 | 52 | 0.5600 | 0.6582 |
85
+ | 0.4961 | 16.0 | 56 | 0.5889 | 0.6709 |
86
+ | 0.4961 | 16.8571 | 59 | 0.8381 | 0.6835 |
87
+ | 0.4391 | 18.0 | 63 | 0.6725 | 0.6962 |
88
+ | 0.4391 | 18.8571 | 66 | 0.5350 | 0.7215 |
89
+ | 0.413 | 20.0 | 70 | 0.6033 | 0.7089 |
90
+ | 0.413 | 20.8571 | 73 | 0.7280 | 0.6835 |
91
+ | 0.413 | 22.0 | 77 | 0.6082 | 0.7342 |
92
+ | 0.336 | 22.8571 | 80 | 0.6530 | 0.7595 |
93
+ | 0.336 | 24.0 | 84 | 0.6922 | 0.7089 |
94
+ | 0.336 | 24.8571 | 87 | 0.6649 | 0.7089 |
95
+ | 0.2745 | 26.0 | 91 | 0.7311 | 0.7089 |
96
+ | 0.2745 | 26.8571 | 94 | 0.7192 | 0.7089 |
97
+ | 0.2745 | 28.0 | 98 | 0.7408 | 0.7215 |
98
+ | 0.2494 | 28.8571 | 101 | 0.5842 | 0.8101 |
99
+ | 0.2494 | 30.0 | 105 | 0.5949 | 0.7595 |
100
+ | 0.2494 | 30.8571 | 108 | 0.6885 | 0.7468 |
101
+ | 0.2291 | 32.0 | 112 | 0.8746 | 0.7089 |
102
+ | 0.2291 | 32.8571 | 115 | 0.8005 | 0.7089 |
103
+ | 0.2291 | 34.0 | 119 | 0.7034 | 0.7342 |
104
+ | 0.2 | 34.8571 | 122 | 0.7047 | 0.7089 |
105
+ | 0.2 | 36.0 | 126 | 0.8362 | 0.7342 |
106
+ | 0.2 | 36.8571 | 129 | 0.8509 | 0.7468 |
107
+ | 0.1674 | 38.0 | 133 | 0.9237 | 0.7595 |
108
+ | 0.1674 | 38.8571 | 136 | 0.7527 | 0.7595 |
109
+ | 0.1764 | 40.0 | 140 | 0.7904 | 0.7468 |
110
+ | 0.1764 | 40.8571 | 143 | 0.7333 | 0.7595 |
111
+ | 0.1764 | 42.0 | 147 | 0.7778 | 0.7342 |
112
+ | 0.1706 | 42.8571 | 150 | 0.7342 | 0.7722 |
113
+ | 0.1706 | 44.0 | 154 | 0.8144 | 0.7468 |
114
+ | 0.1706 | 44.8571 | 157 | 0.8299 | 0.7595 |
115
+ | 0.1617 | 46.0 | 161 | 1.0111 | 0.7468 |
116
+ | 0.1617 | 46.8571 | 164 | 0.8602 | 0.7595 |
117
+ | 0.1617 | 48.0 | 168 | 0.8332 | 0.7342 |
118
+ | 0.1622 | 48.8571 | 171 | 0.8297 | 0.7468 |
119
+ | 0.1622 | 50.0 | 175 | 0.8817 | 0.7595 |
120
+ | 0.1622 | 50.8571 | 178 | 0.8742 | 0.7595 |
121
+ | 0.1437 | 52.0 | 182 | 1.0696 | 0.7595 |
122
+ | 0.1437 | 52.8571 | 185 | 0.9412 | 0.7595 |
123
+ | 0.1437 | 54.0 | 189 | 0.7411 | 0.7975 |
124
+ | 0.1492 | 54.8571 | 192 | 0.9043 | 0.7595 |
125
+ | 0.1492 | 56.0 | 196 | 0.7936 | 0.7848 |
126
+ | 0.1492 | 56.8571 | 199 | 0.8231 | 0.7722 |
127
+ | 0.1279 | 58.0 | 203 | 1.0894 | 0.7722 |
128
+ | 0.1279 | 58.8571 | 206 | 1.0071 | 0.7975 |
129
+ | 0.1317 | 60.0 | 210 | 0.9893 | 0.7722 |
130
+ | 0.1317 | 60.8571 | 213 | 1.0476 | 0.7468 |
131
+ | 0.1317 | 62.0 | 217 | 0.8081 | 0.7848 |
132
+ | 0.1456 | 62.8571 | 220 | 0.8136 | 0.7468 |
133
+ | 0.1456 | 64.0 | 224 | 0.9613 | 0.7848 |
134
+ | 0.1456 | 64.8571 | 227 | 0.9783 | 0.7848 |
135
+ | 0.119 | 66.0 | 231 | 1.0226 | 0.7722 |
136
+ | 0.119 | 66.8571 | 234 | 1.0810 | 0.7722 |
137
+ | 0.119 | 68.0 | 238 | 0.9606 | 0.7975 |
138
+ | 0.1323 | 68.8571 | 241 | 0.9852 | 0.7848 |
139
+ | 0.1323 | 70.0 | 245 | 0.8826 | 0.7595 |
140
+ | 0.1323 | 70.8571 | 248 | 0.8169 | 0.7468 |
141
+ | 0.126 | 72.0 | 252 | 0.8815 | 0.7595 |
142
+ | 0.126 | 72.8571 | 255 | 0.9871 | 0.7722 |
143
+ | 0.126 | 74.0 | 259 | 0.8927 | 0.7722 |
144
+ | 0.1013 | 74.8571 | 262 | 0.8365 | 0.7468 |
145
+ | 0.1013 | 76.0 | 266 | 0.8423 | 0.7468 |
146
+ | 0.1013 | 76.8571 | 269 | 0.8331 | 0.7468 |
147
+ | 0.1142 | 78.0 | 273 | 0.8204 | 0.7722 |
148
+ | 0.1142 | 78.8571 | 276 | 0.8286 | 0.7722 |
149
+ | 0.1287 | 80.0 | 280 | 0.8702 | 0.7722 |
150
+ | 0.1287 | 80.8571 | 283 | 0.9070 | 0.7722 |
151
+ | 0.1287 | 82.0 | 287 | 0.9025 | 0.7722 |
152
+ | 0.099 | 82.8571 | 290 | 0.8806 | 0.7722 |
153
+ | 0.099 | 84.0 | 294 | 0.8637 | 0.7595 |
154
+ | 0.099 | 84.8571 | 297 | 0.8578 | 0.7595 |
155
+ | 0.1141 | 85.7143 | 300 | 0.8551 | 0.7468 |
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 sha256:8ad8aa5eba7e13b92a76639d62f8334c68e2fef1469711547e7255779a944743
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5187feffd8d76ac24cd05e2f790c9e5add340c3cb5707e6e26662166d670aef5
3
  size 343230408
runs/May21_20-13-34_804716d6a90a/events.out.tfevents.1716322415.804716d6a90a.958.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3e5efb8de4457e5ae09bef38b88c0be1d9cf4166bdd42c82db0f3d9a756c79f
3
- size 38755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc9e99714aa8aae628e1d94862d27b200f576e5c00e4490f32647e205c27305
3
+ size 39109