Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-75-fold4

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
4504516
•
1 Parent(s): 4d97278

Model save

Browse files
Files changed (3) hide show
  1. README.md +177 -0
  2. model.safetensors +1 -1
  3. runs/May22_01-20-41_804716d6a90a/events.out.tfevents.1716340842.804716d6a90a.958.26 +2 -2
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-patch16-224-75-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: 0.9069767441860465
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-patch16-224-75-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: 0.3693
36
+ - Accuracy: 0.9070
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 | 0.5613 | 0.6744 |
71
+ | No log | 2.0 | 4 | 0.6233 | 0.6977 |
72
+ | No log | 3.0 | 6 | 0.7506 | 0.6977 |
73
+ | No log | 4.0 | 8 | 0.6462 | 0.6977 |
74
+ | 0.5231 | 5.0 | 10 | 0.3889 | 0.8140 |
75
+ | 0.5231 | 6.0 | 12 | 0.3485 | 0.8372 |
76
+ | 0.5231 | 7.0 | 14 | 0.4327 | 0.8372 |
77
+ | 0.5231 | 8.0 | 16 | 0.4470 | 0.8372 |
78
+ | 0.5231 | 9.0 | 18 | 0.3067 | 0.8605 |
79
+ | 0.3699 | 10.0 | 20 | 0.3075 | 0.8605 |
80
+ | 0.3699 | 11.0 | 22 | 0.5433 | 0.8372 |
81
+ | 0.3699 | 12.0 | 24 | 0.5849 | 0.8140 |
82
+ | 0.3699 | 13.0 | 26 | 0.4509 | 0.8372 |
83
+ | 0.3699 | 14.0 | 28 | 0.5410 | 0.8372 |
84
+ | 0.2951 | 15.0 | 30 | 0.4710 | 0.8140 |
85
+ | 0.2951 | 16.0 | 32 | 0.3738 | 0.8605 |
86
+ | 0.2951 | 17.0 | 34 | 0.3704 | 0.8372 |
87
+ | 0.2951 | 18.0 | 36 | 0.2682 | 0.9070 |
88
+ | 0.2951 | 19.0 | 38 | 0.4187 | 0.8372 |
89
+ | 0.2279 | 20.0 | 40 | 0.3961 | 0.8372 |
90
+ | 0.2279 | 21.0 | 42 | 0.2976 | 0.8837 |
91
+ | 0.2279 | 22.0 | 44 | 0.5655 | 0.8140 |
92
+ | 0.2279 | 23.0 | 46 | 0.4931 | 0.8372 |
93
+ | 0.2279 | 24.0 | 48 | 0.2672 | 0.9070 |
94
+ | 0.1823 | 25.0 | 50 | 0.2795 | 0.9070 |
95
+ | 0.1823 | 26.0 | 52 | 0.3885 | 0.8605 |
96
+ | 0.1823 | 27.0 | 54 | 0.2779 | 0.9070 |
97
+ | 0.1823 | 28.0 | 56 | 0.2990 | 0.8605 |
98
+ | 0.1823 | 29.0 | 58 | 0.3090 | 0.8605 |
99
+ | 0.1314 | 30.0 | 60 | 0.2564 | 0.9302 |
100
+ | 0.1314 | 31.0 | 62 | 0.2825 | 0.8605 |
101
+ | 0.1314 | 32.0 | 64 | 0.3655 | 0.8605 |
102
+ | 0.1314 | 33.0 | 66 | 0.2486 | 0.9302 |
103
+ | 0.1314 | 34.0 | 68 | 0.2734 | 0.9070 |
104
+ | 0.1387 | 35.0 | 70 | 0.5242 | 0.8372 |
105
+ | 0.1387 | 36.0 | 72 | 0.5958 | 0.8372 |
106
+ | 0.1387 | 37.0 | 74 | 0.3472 | 0.8837 |
107
+ | 0.1387 | 38.0 | 76 | 0.3057 | 0.9070 |
108
+ | 0.1387 | 39.0 | 78 | 0.4018 | 0.8372 |
109
+ | 0.1266 | 40.0 | 80 | 0.3940 | 0.8372 |
110
+ | 0.1266 | 41.0 | 82 | 0.3568 | 0.8605 |
111
+ | 0.1266 | 42.0 | 84 | 0.3533 | 0.8837 |
112
+ | 0.1266 | 43.0 | 86 | 0.3451 | 0.8837 |
113
+ | 0.1266 | 44.0 | 88 | 0.3478 | 0.9070 |
114
+ | 0.1004 | 45.0 | 90 | 0.3195 | 0.9302 |
115
+ | 0.1004 | 46.0 | 92 | 0.3926 | 0.9070 |
116
+ | 0.1004 | 47.0 | 94 | 0.4169 | 0.8837 |
117
+ | 0.1004 | 48.0 | 96 | 0.4274 | 0.8837 |
118
+ | 0.1004 | 49.0 | 98 | 0.4061 | 0.9070 |
119
+ | 0.1033 | 50.0 | 100 | 0.4277 | 0.8605 |
120
+ | 0.1033 | 51.0 | 102 | 0.3977 | 0.9070 |
121
+ | 0.1033 | 52.0 | 104 | 0.4428 | 0.8605 |
122
+ | 0.1033 | 53.0 | 106 | 0.6753 | 0.8140 |
123
+ | 0.1033 | 54.0 | 108 | 0.6912 | 0.8140 |
124
+ | 0.0827 | 55.0 | 110 | 0.4201 | 0.8605 |
125
+ | 0.0827 | 56.0 | 112 | 0.3086 | 0.9302 |
126
+ | 0.0827 | 57.0 | 114 | 0.3150 | 0.9302 |
127
+ | 0.0827 | 58.0 | 116 | 0.4757 | 0.8605 |
128
+ | 0.0827 | 59.0 | 118 | 0.6409 | 0.8605 |
129
+ | 0.0889 | 60.0 | 120 | 0.5430 | 0.8837 |
130
+ | 0.0889 | 61.0 | 122 | 0.4044 | 0.8837 |
131
+ | 0.0889 | 62.0 | 124 | 0.3473 | 0.9302 |
132
+ | 0.0889 | 63.0 | 126 | 0.3485 | 0.9302 |
133
+ | 0.0889 | 64.0 | 128 | 0.3711 | 0.9302 |
134
+ | 0.088 | 65.0 | 130 | 0.4405 | 0.8837 |
135
+ | 0.088 | 66.0 | 132 | 0.6526 | 0.8605 |
136
+ | 0.088 | 67.0 | 134 | 0.7019 | 0.8605 |
137
+ | 0.088 | 68.0 | 136 | 0.5408 | 0.8605 |
138
+ | 0.088 | 69.0 | 138 | 0.4057 | 0.9302 |
139
+ | 0.0734 | 70.0 | 140 | 0.3797 | 0.9302 |
140
+ | 0.0734 | 71.0 | 142 | 0.3811 | 0.9302 |
141
+ | 0.0734 | 72.0 | 144 | 0.4040 | 0.9302 |
142
+ | 0.0734 | 73.0 | 146 | 0.4567 | 0.8837 |
143
+ | 0.0734 | 74.0 | 148 | 0.5161 | 0.9070 |
144
+ | 0.0721 | 75.0 | 150 | 0.5240 | 0.8837 |
145
+ | 0.0721 | 76.0 | 152 | 0.5048 | 0.9070 |
146
+ | 0.0721 | 77.0 | 154 | 0.4635 | 0.9070 |
147
+ | 0.0721 | 78.0 | 156 | 0.4510 | 0.9070 |
148
+ | 0.0721 | 79.0 | 158 | 0.4931 | 0.9070 |
149
+ | 0.0592 | 80.0 | 160 | 0.5368 | 0.8837 |
150
+ | 0.0592 | 81.0 | 162 | 0.5297 | 0.8837 |
151
+ | 0.0592 | 82.0 | 164 | 0.4722 | 0.9070 |
152
+ | 0.0592 | 83.0 | 166 | 0.4179 | 0.9302 |
153
+ | 0.0592 | 84.0 | 168 | 0.4045 | 0.9302 |
154
+ | 0.0634 | 85.0 | 170 | 0.4200 | 0.9302 |
155
+ | 0.0634 | 86.0 | 172 | 0.4497 | 0.9302 |
156
+ | 0.0634 | 87.0 | 174 | 0.4796 | 0.9070 |
157
+ | 0.0634 | 88.0 | 176 | 0.4997 | 0.8837 |
158
+ | 0.0634 | 89.0 | 178 | 0.4867 | 0.8837 |
159
+ | 0.0758 | 90.0 | 180 | 0.4478 | 0.9302 |
160
+ | 0.0758 | 91.0 | 182 | 0.4145 | 0.9302 |
161
+ | 0.0758 | 92.0 | 184 | 0.4036 | 0.9302 |
162
+ | 0.0758 | 93.0 | 186 | 0.3877 | 0.9302 |
163
+ | 0.0758 | 94.0 | 188 | 0.3747 | 0.9070 |
164
+ | 0.0529 | 95.0 | 190 | 0.3685 | 0.9070 |
165
+ | 0.0529 | 96.0 | 192 | 0.3644 | 0.9070 |
166
+ | 0.0529 | 97.0 | 194 | 0.3648 | 0.9070 |
167
+ | 0.0529 | 98.0 | 196 | 0.3663 | 0.9070 |
168
+ | 0.0529 | 99.0 | 198 | 0.3686 | 0.9070 |
169
+ | 0.0594 | 100.0 | 200 | 0.3693 | 0.9070 |
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 sha256:040705c3dc51dda64e8a13a9b799251480923597529b007ce7b9e0f023179234
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8818fc762bb3c1121993ceb24bcfaf738f27c9621d37c19a791dd9401c1cd0
3
  size 343230408
runs/May22_01-20-41_804716d6a90a/events.out.tfevents.1716340842.804716d6a90a.958.26 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5367628ea0cbf7006cf5eb53e93ff933c27472c24eb502b9ba6540ba054fcc38
3
- size 40471
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8fa4c61e38f660344c9b6f7007bbd8187ed04067d54edcd96d13d4a4430a98
3
+ size 41359