Hugging Face's logo

BilalMuftuoglu
/
deit-base-distilled-patch16-224-85-fold4

Image Classification
Transformers
TensorBoard
Safetensors
deit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
cb14296
·
verified ·
1 Parent(s): 6250c1a

Model save

Browse files
Files changed (3) hide show
  1. README.md +177 -0
  2. model.safetensors +1 -1
  3. runs/May22_12-25-56_927069b479b5/events.out.tfevents.1716380757.927069b479b5.252.2 +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-patch16-224-85-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: 0.8636363636363636
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-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: 0.4002
36
+ - Accuracy: 0.8636
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 | 0.6100 | 0.7273 |
71
+ | No log | 2.0 | 4 | 0.6938 | 0.7045 |
72
+ | No log | 3.0 | 6 | 0.7568 | 0.7045 |
73
+ | No log | 4.0 | 8 | 0.6140 | 0.7045 |
74
+ | 0.5388 | 5.0 | 10 | 0.4976 | 0.75 |
75
+ | 0.5388 | 6.0 | 12 | 0.4809 | 0.7273 |
76
+ | 0.5388 | 7.0 | 14 | 0.5276 | 0.7273 |
77
+ | 0.5388 | 8.0 | 16 | 0.4455 | 0.7955 |
78
+ | 0.5388 | 9.0 | 18 | 0.3915 | 0.8409 |
79
+ | 0.4154 | 10.0 | 20 | 0.5070 | 0.7955 |
80
+ | 0.4154 | 11.0 | 22 | 0.3747 | 0.8182 |
81
+ | 0.4154 | 12.0 | 24 | 0.3027 | 0.8864 |
82
+ | 0.4154 | 13.0 | 26 | 0.3053 | 0.8636 |
83
+ | 0.4154 | 14.0 | 28 | 0.3194 | 0.8409 |
84
+ | 0.3258 | 15.0 | 30 | 0.3134 | 0.8864 |
85
+ | 0.3258 | 16.0 | 32 | 0.2925 | 0.8864 |
86
+ | 0.3258 | 17.0 | 34 | 0.2449 | 0.8864 |
87
+ | 0.3258 | 18.0 | 36 | 0.2308 | 0.8864 |
88
+ | 0.3258 | 19.0 | 38 | 0.2141 | 0.9318 |
89
+ | 0.2528 | 20.0 | 40 | 0.2330 | 0.9318 |
90
+ | 0.2528 | 21.0 | 42 | 0.2173 | 0.9318 |
91
+ | 0.2528 | 22.0 | 44 | 0.2450 | 0.9091 |
92
+ | 0.2528 | 23.0 | 46 | 0.2549 | 0.9091 |
93
+ | 0.2528 | 24.0 | 48 | 0.4341 | 0.75 |
94
+ | 0.175 | 25.0 | 50 | 0.2358 | 0.9091 |
95
+ | 0.175 | 26.0 | 52 | 0.2828 | 0.8864 |
96
+ | 0.175 | 27.0 | 54 | 0.2236 | 0.9091 |
97
+ | 0.175 | 28.0 | 56 | 0.2591 | 0.8636 |
98
+ | 0.175 | 29.0 | 58 | 0.2702 | 0.8864 |
99
+ | 0.169 | 30.0 | 60 | 0.2910 | 0.8636 |
100
+ | 0.169 | 31.0 | 62 | 0.3594 | 0.9091 |
101
+ | 0.169 | 32.0 | 64 | 0.4246 | 0.8864 |
102
+ | 0.169 | 33.0 | 66 | 0.2655 | 0.8864 |
103
+ | 0.169 | 34.0 | 68 | 0.2581 | 0.8864 |
104
+ | 0.1336 | 35.0 | 70 | 0.2494 | 0.8409 |
105
+ | 0.1336 | 36.0 | 72 | 0.2438 | 0.8636 |
106
+ | 0.1336 | 37.0 | 74 | 0.3246 | 0.8636 |
107
+ | 0.1336 | 38.0 | 76 | 0.2887 | 0.8409 |
108
+ | 0.1336 | 39.0 | 78 | 0.3559 | 0.8409 |
109
+ | 0.1281 | 40.0 | 80 | 0.3274 | 0.8864 |
110
+ | 0.1281 | 41.0 | 82 | 0.3371 | 0.8409 |
111
+ | 0.1281 | 42.0 | 84 | 0.3902 | 0.8409 |
112
+ | 0.1281 | 43.0 | 86 | 0.3100 | 0.8409 |
113
+ | 0.1281 | 44.0 | 88 | 0.3113 | 0.8636 |
114
+ | 0.136 | 45.0 | 90 | 0.3244 | 0.8409 |
115
+ | 0.136 | 46.0 | 92 | 0.3765 | 0.8864 |
116
+ | 0.136 | 47.0 | 94 | 0.3838 | 0.8864 |
117
+ | 0.136 | 48.0 | 96 | 0.3845 | 0.7955 |
118
+ | 0.136 | 49.0 | 98 | 0.3910 | 0.7955 |
119
+ | 0.0934 | 50.0 | 100 | 0.4889 | 0.8636 |
120
+ | 0.0934 | 51.0 | 102 | 0.6680 | 0.8182 |
121
+ | 0.0934 | 52.0 | 104 | 0.4264 | 0.8864 |
122
+ | 0.0934 | 53.0 | 106 | 0.3266 | 0.8182 |
123
+ | 0.0934 | 54.0 | 108 | 0.3168 | 0.8864 |
124
+ | 0.0999 | 55.0 | 110 | 0.3671 | 0.8182 |
125
+ | 0.0999 | 56.0 | 112 | 0.4684 | 0.8182 |
126
+ | 0.0999 | 57.0 | 114 | 0.4254 | 0.8182 |
127
+ | 0.0999 | 58.0 | 116 | 0.3195 | 0.8182 |
128
+ | 0.0999 | 59.0 | 118 | 0.3860 | 0.8864 |
129
+ | 0.1145 | 60.0 | 120 | 0.4805 | 0.8636 |
130
+ | 0.1145 | 61.0 | 122 | 0.3864 | 0.8182 |
131
+ | 0.1145 | 62.0 | 124 | 0.3347 | 0.8182 |
132
+ | 0.1145 | 63.0 | 126 | 0.3144 | 0.8182 |
133
+ | 0.1145 | 64.0 | 128 | 0.3267 | 0.8636 |
134
+ | 0.0769 | 65.0 | 130 | 0.3592 | 0.8636 |
135
+ | 0.0769 | 66.0 | 132 | 0.3520 | 0.8636 |
136
+ | 0.0769 | 67.0 | 134 | 0.3632 | 0.8636 |
137
+ | 0.0769 | 68.0 | 136 | 0.3955 | 0.8636 |
138
+ | 0.0769 | 69.0 | 138 | 0.4053 | 0.8182 |
139
+ | 0.0976 | 70.0 | 140 | 0.4272 | 0.8636 |
140
+ | 0.0976 | 71.0 | 142 | 0.4345 | 0.8409 |
141
+ | 0.0976 | 72.0 | 144 | 0.3943 | 0.8636 |
142
+ | 0.0976 | 73.0 | 146 | 0.3827 | 0.8636 |
143
+ | 0.0976 | 74.0 | 148 | 0.4133 | 0.8409 |
144
+ | 0.0981 | 75.0 | 150 | 0.4311 | 0.8409 |
145
+ | 0.0981 | 76.0 | 152 | 0.4126 | 0.8409 |
146
+ | 0.0981 | 77.0 | 154 | 0.3651 | 0.8636 |
147
+ | 0.0981 | 78.0 | 156 | 0.3511 | 0.8182 |
148
+ | 0.0981 | 79.0 | 158 | 0.3625 | 0.8636 |
149
+ | 0.085 | 80.0 | 160 | 0.3607 | 0.8636 |
150
+ | 0.085 | 81.0 | 162 | 0.3470 | 0.8409 |
151
+ | 0.085 | 82.0 | 164 | 0.3639 | 0.8409 |
152
+ | 0.085 | 83.0 | 166 | 0.3750 | 0.8409 |
153
+ | 0.085 | 84.0 | 168 | 0.3726 | 0.7955 |
154
+ | 0.0831 | 85.0 | 170 | 0.3740 | 0.8182 |
155
+ | 0.0831 | 86.0 | 172 | 0.3807 | 0.8636 |
156
+ | 0.0831 | 87.0 | 174 | 0.3875 | 0.8636 |
157
+ | 0.0831 | 88.0 | 176 | 0.3886 | 0.8409 |
158
+ | 0.0831 | 89.0 | 178 | 0.4017 | 0.7955 |
159
+ | 0.0811 | 90.0 | 180 | 0.4271 | 0.7955 |
160
+ | 0.0811 | 91.0 | 182 | 0.4293 | 0.7955 |
161
+ | 0.0811 | 92.0 | 184 | 0.4243 | 0.7727 |
162
+ | 0.0811 | 93.0 | 186 | 0.4088 | 0.7727 |
163
+ | 0.0811 | 94.0 | 188 | 0.3986 | 0.7955 |
164
+ | 0.0692 | 95.0 | 190 | 0.3963 | 0.8182 |
165
+ | 0.0692 | 96.0 | 192 | 0.3987 | 0.8636 |
166
+ | 0.0692 | 97.0 | 194 | 0.4020 | 0.8636 |
167
+ | 0.0692 | 98.0 | 196 | 0.4015 | 0.8636 |
168
+ | 0.0692 | 99.0 | 198 | 0.4009 | 0.8636 |
169
+ | 0.0644 | 100.0 | 200 | 0.4002 | 0.8636 |
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 sha256:0e14f383bedee00d8e00b7e1f7d17e647290fecd8fd977463da5fae09d961a7c
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccccabec2c0bec67dad07473cf5d960aabb8c5ea4039e036df2f796a0a1caf2a
3
  size 343230408
runs/May22_12-25-56_927069b479b5/events.out.tfevents.1716380757.927069b479b5.252.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f48796dedeabac6f768559f9c8903f1b28b3fc6b0d759de8da19bbe485aac1a7
3
- size 40148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e724e5ed805f2aa69d5af306f9ab6a7993c84a6d26309c48ece5ce2a00cb7a08
3
+ size 41359