BilalMuftuoglu commited on
Commit
2f77cf8
1 Parent(s): 039dd56

Model save

Browse files
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-patch16-224-85-fold5
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: 0.8863636363636364
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-patch16-224-85-fold5
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: 0.2976
36
+ - Accuracy: 0.8864
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 | 1.1685 | 0.3182 |
71
+ | No log | 2.0 | 4 | 0.7295 | 0.4545 |
72
+ | No log | 3.0 | 6 | 0.6641 | 0.7045 |
73
+ | No log | 4.0 | 8 | 0.7703 | 0.7045 |
74
+ | 0.7885 | 5.0 | 10 | 0.6750 | 0.7045 |
75
+ | 0.7885 | 6.0 | 12 | 0.6446 | 0.7045 |
76
+ | 0.7885 | 7.0 | 14 | 0.6919 | 0.7045 |
77
+ | 0.7885 | 8.0 | 16 | 0.6489 | 0.7045 |
78
+ | 0.7885 | 9.0 | 18 | 0.5245 | 0.7273 |
79
+ | 0.4488 | 10.0 | 20 | 0.8494 | 0.7045 |
80
+ | 0.4488 | 11.0 | 22 | 0.9086 | 0.6818 |
81
+ | 0.4488 | 12.0 | 24 | 0.5250 | 0.75 |
82
+ | 0.4488 | 13.0 | 26 | 0.5179 | 0.7727 |
83
+ | 0.4488 | 14.0 | 28 | 0.4423 | 0.7727 |
84
+ | 0.3387 | 15.0 | 30 | 0.5114 | 0.7273 |
85
+ | 0.3387 | 16.0 | 32 | 0.5048 | 0.75 |
86
+ | 0.3387 | 17.0 | 34 | 0.4997 | 0.7045 |
87
+ | 0.3387 | 18.0 | 36 | 0.4776 | 0.7045 |
88
+ | 0.3387 | 19.0 | 38 | 0.4138 | 0.7955 |
89
+ | 0.24 | 20.0 | 40 | 0.3220 | 0.8864 |
90
+ | 0.24 | 21.0 | 42 | 0.3363 | 0.8409 |
91
+ | 0.24 | 22.0 | 44 | 0.2958 | 0.8636 |
92
+ | 0.24 | 23.0 | 46 | 0.3098 | 0.8636 |
93
+ | 0.24 | 24.0 | 48 | 0.4030 | 0.8636 |
94
+ | 0.1524 | 25.0 | 50 | 0.3094 | 0.8636 |
95
+ | 0.1524 | 26.0 | 52 | 0.2721 | 0.8864 |
96
+ | 0.1524 | 27.0 | 54 | 0.3363 | 0.8636 |
97
+ | 0.1524 | 28.0 | 56 | 0.2731 | 0.8636 |
98
+ | 0.1524 | 29.0 | 58 | 0.5660 | 0.7955 |
99
+ | 0.1646 | 30.0 | 60 | 0.4949 | 0.8409 |
100
+ | 0.1646 | 31.0 | 62 | 0.4087 | 0.7727 |
101
+ | 0.1646 | 32.0 | 64 | 0.4467 | 0.8409 |
102
+ | 0.1646 | 33.0 | 66 | 0.4130 | 0.8182 |
103
+ | 0.1646 | 34.0 | 68 | 0.3727 | 0.8409 |
104
+ | 0.136 | 35.0 | 70 | 0.5894 | 0.7727 |
105
+ | 0.136 | 36.0 | 72 | 0.9462 | 0.75 |
106
+ | 0.136 | 37.0 | 74 | 0.5926 | 0.7273 |
107
+ | 0.136 | 38.0 | 76 | 0.3138 | 0.8864 |
108
+ | 0.136 | 39.0 | 78 | 0.4173 | 0.8864 |
109
+ | 0.163 | 40.0 | 80 | 0.3154 | 0.8636 |
110
+ | 0.163 | 41.0 | 82 | 0.3235 | 0.8636 |
111
+ | 0.163 | 42.0 | 84 | 0.3902 | 0.8182 |
112
+ | 0.163 | 43.0 | 86 | 0.3699 | 0.7955 |
113
+ | 0.163 | 44.0 | 88 | 0.4311 | 0.8182 |
114
+ | 0.1018 | 45.0 | 90 | 0.3071 | 0.9091 |
115
+ | 0.1018 | 46.0 | 92 | 0.2849 | 0.9091 |
116
+ | 0.1018 | 47.0 | 94 | 0.3226 | 0.8409 |
117
+ | 0.1018 | 48.0 | 96 | 0.2967 | 0.8409 |
118
+ | 0.1018 | 49.0 | 98 | 0.2936 | 0.8636 |
119
+ | 0.0957 | 50.0 | 100 | 0.2737 | 0.8864 |
120
+ | 0.0957 | 51.0 | 102 | 0.2845 | 0.8864 |
121
+ | 0.0957 | 52.0 | 104 | 0.3300 | 0.8409 |
122
+ | 0.0957 | 53.0 | 106 | 0.4029 | 0.8409 |
123
+ | 0.0957 | 54.0 | 108 | 0.4279 | 0.8182 |
124
+ | 0.1036 | 55.0 | 110 | 0.3900 | 0.8182 |
125
+ | 0.1036 | 56.0 | 112 | 0.4038 | 0.8636 |
126
+ | 0.1036 | 57.0 | 114 | 0.3569 | 0.8409 |
127
+ | 0.1036 | 58.0 | 116 | 0.5611 | 0.8182 |
128
+ | 0.1036 | 59.0 | 118 | 0.6900 | 0.8182 |
129
+ | 0.1048 | 60.0 | 120 | 0.5679 | 0.8182 |
130
+ | 0.1048 | 61.0 | 122 | 0.4567 | 0.8182 |
131
+ | 0.1048 | 62.0 | 124 | 0.3815 | 0.7955 |
132
+ | 0.1048 | 63.0 | 126 | 0.3546 | 0.7955 |
133
+ | 0.1048 | 64.0 | 128 | 0.3654 | 0.7955 |
134
+ | 0.0928 | 65.0 | 130 | 0.3337 | 0.8864 |
135
+ | 0.0928 | 66.0 | 132 | 0.4161 | 0.8409 |
136
+ | 0.0928 | 67.0 | 134 | 0.3615 | 0.8409 |
137
+ | 0.0928 | 68.0 | 136 | 0.4061 | 0.8182 |
138
+ | 0.0928 | 69.0 | 138 | 0.4191 | 0.8182 |
139
+ | 0.1091 | 70.0 | 140 | 0.3978 | 0.7955 |
140
+ | 0.1091 | 71.0 | 142 | 0.5168 | 0.75 |
141
+ | 0.1091 | 72.0 | 144 | 0.5268 | 0.75 |
142
+ | 0.1091 | 73.0 | 146 | 0.5667 | 0.7955 |
143
+ | 0.1091 | 74.0 | 148 | 0.5396 | 0.7727 |
144
+ | 0.1009 | 75.0 | 150 | 0.4807 | 0.75 |
145
+ | 0.1009 | 76.0 | 152 | 0.3957 | 0.8182 |
146
+ | 0.1009 | 77.0 | 154 | 0.3519 | 0.8636 |
147
+ | 0.1009 | 78.0 | 156 | 0.3654 | 0.8636 |
148
+ | 0.1009 | 79.0 | 158 | 0.3577 | 0.8409 |
149
+ | 0.0836 | 80.0 | 160 | 0.3216 | 0.8636 |
150
+ | 0.0836 | 81.0 | 162 | 0.3132 | 0.8409 |
151
+ | 0.0836 | 82.0 | 164 | 0.3003 | 0.8636 |
152
+ | 0.0836 | 83.0 | 166 | 0.3024 | 0.8636 |
153
+ | 0.0836 | 84.0 | 168 | 0.3214 | 0.8409 |
154
+ | 0.0928 | 85.0 | 170 | 0.3306 | 0.8182 |
155
+ | 0.0928 | 86.0 | 172 | 0.3284 | 0.8409 |
156
+ | 0.0928 | 87.0 | 174 | 0.3272 | 0.8182 |
157
+ | 0.0928 | 88.0 | 176 | 0.3261 | 0.8182 |
158
+ | 0.0928 | 89.0 | 178 | 0.3099 | 0.8409 |
159
+ | 0.0915 | 90.0 | 180 | 0.2928 | 0.8409 |
160
+ | 0.0915 | 91.0 | 182 | 0.2848 | 0.8409 |
161
+ | 0.0915 | 92.0 | 184 | 0.2827 | 0.8409 |
162
+ | 0.0915 | 93.0 | 186 | 0.2885 | 0.8636 |
163
+ | 0.0915 | 94.0 | 188 | 0.3084 | 0.8864 |
164
+ | 0.0775 | 95.0 | 190 | 0.3321 | 0.8409 |
165
+ | 0.0775 | 96.0 | 192 | 0.3358 | 0.8636 |
166
+ | 0.0775 | 97.0 | 194 | 0.3221 | 0.8409 |
167
+ | 0.0775 | 98.0 | 196 | 0.3096 | 0.8636 |
168
+ | 0.0775 | 99.0 | 198 | 0.3007 | 0.8864 |
169
+ | 0.091 | 100.0 | 200 | 0.2976 | 0.8864 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.41.0
175
+ - Pytorch 2.3.0+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 sha256:2bd2120ac22f5021a6a42297d6eb9d7aae7c915fc8b1a0a0b08b5c1cd626e7eb
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbef7cea4c0ee03563b6248d370cb4fa98bbbf1df92efcc052b442589b7d945c
3
  size 343230408
runs/May22_12-44-53_927069b479b5/events.out.tfevents.1716381894.927069b479b5.252.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f28fa1356250f239b8ae28bd3f9829e036954314fb6b3e01c3056c820178384
3
- size 40148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231170119aa7c599cfdc2a2220d9dde99b3dc07fc25368c434be1a54fa7df88b
3
+ size 41359