BilalMuftuoglu commited on
Commit
31707ff
1 Parent(s): fbfb75b

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-patch16-224-75-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: 0.8837209302325582
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-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: 0.2739
36
+ - Accuracy: 0.8837
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 | 0.5697 | 0.6744 |
71
+ | No log | 2.0 | 4 | 0.6348 | 0.6977 |
72
+ | No log | 3.0 | 6 | 0.8030 | 0.6977 |
73
+ | No log | 4.0 | 8 | 0.7092 | 0.6977 |
74
+ | 0.5313 | 5.0 | 10 | 0.4644 | 0.8140 |
75
+ | 0.5313 | 6.0 | 12 | 0.4211 | 0.7907 |
76
+ | 0.5313 | 7.0 | 14 | 0.4913 | 0.8140 |
77
+ | 0.5313 | 8.0 | 16 | 0.4788 | 0.8372 |
78
+ | 0.5313 | 9.0 | 18 | 0.3717 | 0.7907 |
79
+ | 0.3672 | 10.0 | 20 | 0.3763 | 0.8140 |
80
+ | 0.3672 | 11.0 | 22 | 0.5082 | 0.8372 |
81
+ | 0.3672 | 12.0 | 24 | 0.3661 | 0.8140 |
82
+ | 0.3672 | 13.0 | 26 | 0.3693 | 0.8140 |
83
+ | 0.3672 | 14.0 | 28 | 0.3808 | 0.8605 |
84
+ | 0.2837 | 15.0 | 30 | 0.3492 | 0.8372 |
85
+ | 0.2837 | 16.0 | 32 | 0.3446 | 0.7907 |
86
+ | 0.2837 | 17.0 | 34 | 0.3909 | 0.8605 |
87
+ | 0.2837 | 18.0 | 36 | 0.4379 | 0.8372 |
88
+ | 0.2837 | 19.0 | 38 | 0.3905 | 0.8140 |
89
+ | 0.2268 | 20.0 | 40 | 0.3453 | 0.8140 |
90
+ | 0.2268 | 21.0 | 42 | 0.4145 | 0.8372 |
91
+ | 0.2268 | 22.0 | 44 | 0.3370 | 0.8372 |
92
+ | 0.2268 | 23.0 | 46 | 0.3502 | 0.8372 |
93
+ | 0.2268 | 24.0 | 48 | 0.3295 | 0.8372 |
94
+ | 0.1735 | 25.0 | 50 | 0.3118 | 0.8837 |
95
+ | 0.1735 | 26.0 | 52 | 0.3050 | 0.8837 |
96
+ | 0.1735 | 27.0 | 54 | 0.6940 | 0.8140 |
97
+ | 0.1735 | 28.0 | 56 | 0.5913 | 0.8372 |
98
+ | 0.1735 | 29.0 | 58 | 0.3190 | 0.8837 |
99
+ | 0.1221 | 30.0 | 60 | 0.4141 | 0.8372 |
100
+ | 0.1221 | 31.0 | 62 | 0.4572 | 0.8372 |
101
+ | 0.1221 | 32.0 | 64 | 0.3048 | 0.8837 |
102
+ | 0.1221 | 33.0 | 66 | 0.3139 | 0.9070 |
103
+ | 0.1221 | 34.0 | 68 | 0.3090 | 0.8837 |
104
+ | 0.1158 | 35.0 | 70 | 0.3393 | 0.8837 |
105
+ | 0.1158 | 36.0 | 72 | 0.3035 | 0.8605 |
106
+ | 0.1158 | 37.0 | 74 | 0.4730 | 0.8140 |
107
+ | 0.1158 | 38.0 | 76 | 0.3788 | 0.8605 |
108
+ | 0.1158 | 39.0 | 78 | 0.2904 | 0.8837 |
109
+ | 0.1075 | 40.0 | 80 | 0.2750 | 0.8837 |
110
+ | 0.1075 | 41.0 | 82 | 0.3328 | 0.8837 |
111
+ | 0.1075 | 42.0 | 84 | 0.2648 | 0.9070 |
112
+ | 0.1075 | 43.0 | 86 | 0.2517 | 0.8837 |
113
+ | 0.1075 | 44.0 | 88 | 0.4402 | 0.8837 |
114
+ | 0.0925 | 45.0 | 90 | 0.4076 | 0.8837 |
115
+ | 0.0925 | 46.0 | 92 | 0.2390 | 0.9070 |
116
+ | 0.0925 | 47.0 | 94 | 0.2176 | 0.9070 |
117
+ | 0.0925 | 48.0 | 96 | 0.2580 | 0.9302 |
118
+ | 0.0925 | 49.0 | 98 | 0.2049 | 0.9070 |
119
+ | 0.1085 | 50.0 | 100 | 0.2244 | 0.8837 |
120
+ | 0.1085 | 51.0 | 102 | 0.2377 | 0.9070 |
121
+ | 0.1085 | 52.0 | 104 | 0.4591 | 0.8372 |
122
+ | 0.1085 | 53.0 | 106 | 0.5054 | 0.8372 |
123
+ | 0.1085 | 54.0 | 108 | 0.2994 | 0.9302 |
124
+ | 0.0876 | 55.0 | 110 | 0.2387 | 0.9070 |
125
+ | 0.0876 | 56.0 | 112 | 0.3078 | 0.9070 |
126
+ | 0.0876 | 57.0 | 114 | 0.4470 | 0.8372 |
127
+ | 0.0876 | 58.0 | 116 | 0.3457 | 0.9070 |
128
+ | 0.0876 | 59.0 | 118 | 0.2655 | 0.9070 |
129
+ | 0.0823 | 60.0 | 120 | 0.2150 | 0.9070 |
130
+ | 0.0823 | 61.0 | 122 | 0.2116 | 0.9070 |
131
+ | 0.0823 | 62.0 | 124 | 0.2305 | 0.9302 |
132
+ | 0.0823 | 63.0 | 126 | 0.2070 | 0.9302 |
133
+ | 0.0823 | 64.0 | 128 | 0.1808 | 0.9070 |
134
+ | 0.0791 | 65.0 | 130 | 0.1669 | 0.9070 |
135
+ | 0.0791 | 66.0 | 132 | 0.1721 | 0.9070 |
136
+ | 0.0791 | 67.0 | 134 | 0.2194 | 0.9302 |
137
+ | 0.0791 | 68.0 | 136 | 0.3454 | 0.8837 |
138
+ | 0.0791 | 69.0 | 138 | 0.5415 | 0.8372 |
139
+ | 0.0607 | 70.0 | 140 | 0.4457 | 0.8605 |
140
+ | 0.0607 | 71.0 | 142 | 0.2411 | 0.8837 |
141
+ | 0.0607 | 72.0 | 144 | 0.2057 | 0.9070 |
142
+ | 0.0607 | 73.0 | 146 | 0.2200 | 0.9070 |
143
+ | 0.0607 | 74.0 | 148 | 0.2677 | 0.8837 |
144
+ | 0.0715 | 75.0 | 150 | 0.2950 | 0.8837 |
145
+ | 0.0715 | 76.0 | 152 | 0.2874 | 0.8837 |
146
+ | 0.0715 | 77.0 | 154 | 0.2236 | 0.9070 |
147
+ | 0.0715 | 78.0 | 156 | 0.2052 | 0.9302 |
148
+ | 0.0715 | 79.0 | 158 | 0.2177 | 0.9535 |
149
+ | 0.0644 | 80.0 | 160 | 0.2178 | 0.9535 |
150
+ | 0.0644 | 81.0 | 162 | 0.2126 | 0.9302 |
151
+ | 0.0644 | 82.0 | 164 | 0.2127 | 0.9302 |
152
+ | 0.0644 | 83.0 | 166 | 0.2216 | 0.9070 |
153
+ | 0.0644 | 84.0 | 168 | 0.2420 | 0.9070 |
154
+ | 0.0622 | 85.0 | 170 | 0.2305 | 0.9070 |
155
+ | 0.0622 | 86.0 | 172 | 0.2247 | 0.9070 |
156
+ | 0.0622 | 87.0 | 174 | 0.2492 | 0.9070 |
157
+ | 0.0622 | 88.0 | 176 | 0.3292 | 0.8837 |
158
+ | 0.0622 | 89.0 | 178 | 0.3876 | 0.8837 |
159
+ | 0.0564 | 90.0 | 180 | 0.3886 | 0.8837 |
160
+ | 0.0564 | 91.0 | 182 | 0.3707 | 0.8837 |
161
+ | 0.0564 | 92.0 | 184 | 0.3377 | 0.8837 |
162
+ | 0.0564 | 93.0 | 186 | 0.3186 | 0.8837 |
163
+ | 0.0564 | 94.0 | 188 | 0.3038 | 0.8837 |
164
+ | 0.0578 | 95.0 | 190 | 0.2818 | 0.8605 |
165
+ | 0.0578 | 96.0 | 192 | 0.2756 | 0.8837 |
166
+ | 0.0578 | 97.0 | 194 | 0.2694 | 0.8837 |
167
+ | 0.0578 | 98.0 | 196 | 0.2698 | 0.8837 |
168
+ | 0.0578 | 99.0 | 198 | 0.2732 | 0.8837 |
169
+ | 0.0424 | 100.0 | 200 | 0.2739 | 0.8837 |
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 sha256:9eb9b1849fcb34e1a8174b36880e356068ae3bc59f080c2c6367043f140aa1d5
3
  size 343230408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eede911b849bc16d34aaf5cb615bed7e78a47070ee727646cbb666743ae0134d
3
  size 343230408
runs/May22_01-01-40_804716d6a90a/events.out.tfevents.1716339701.804716d6a90a.958.24 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b36dfae9fcc24e68b66569fb065ad0446dd295acd27af3bbf35a3484d618b046
3
- size 40471
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec549655f07d4362b1ba8e1b8ed10744eeb8d77882a5235c7089df181eff02f
3
+ size 41359