Hugging Face's logo

BilalMuftuoglu
/
beit-base-patch16-224-55-fold2

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
BilalMuftuoglu commited on
Commit
f929525
•
1 Parent(s): e5c9a03

Model save

Browse files
Files changed (3) hide show
  1. README.md +163 -0
  2. model.safetensors +1 -1
  3. runs/May20_12-47-55_b94dbfcd7693/events.out.tfevents.1716209276.b94dbfcd7693.1289.0 +2 -2
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: beit-base-patch16-224-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: 0.8227848101265823
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
+ # beit-base-patch16-224-fold2
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8061
36
+ - Accuracy: 0.8228
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 | 0.6785 | 0.6076 |
71
+ | No log | 2.0 | 7 | 0.6621 | 0.6329 |
72
+ | 0.7083 | 2.8571 | 10 | 0.6434 | 0.5823 |
73
+ | 0.7083 | 4.0 | 14 | 0.6708 | 0.5696 |
74
+ | 0.7083 | 4.8571 | 17 | 0.6701 | 0.6076 |
75
+ | 0.6009 | 6.0 | 21 | 0.7958 | 0.5949 |
76
+ | 0.6009 | 6.8571 | 24 | 0.5952 | 0.6456 |
77
+ | 0.6009 | 8.0 | 28 | 0.8008 | 0.6962 |
78
+ | 0.5315 | 8.8571 | 31 | 0.8903 | 0.6329 |
79
+ | 0.5315 | 10.0 | 35 | 0.7070 | 0.6709 |
80
+ | 0.5315 | 10.8571 | 38 | 0.5331 | 0.7595 |
81
+ | 0.5756 | 12.0 | 42 | 0.5307 | 0.7468 |
82
+ | 0.5756 | 12.8571 | 45 | 0.5070 | 0.7468 |
83
+ | 0.5756 | 14.0 | 49 | 0.6117 | 0.7215 |
84
+ | 0.4519 | 14.8571 | 52 | 0.4667 | 0.7468 |
85
+ | 0.4519 | 16.0 | 56 | 0.4151 | 0.7848 |
86
+ | 0.4519 | 16.8571 | 59 | 0.4435 | 0.7722 |
87
+ | 0.3821 | 18.0 | 63 | 0.4114 | 0.7975 |
88
+ | 0.3821 | 18.8571 | 66 | 0.4067 | 0.8101 |
89
+ | 0.328 | 20.0 | 70 | 0.4459 | 0.8101 |
90
+ | 0.328 | 20.8571 | 73 | 0.3859 | 0.8354 |
91
+ | 0.328 | 22.0 | 77 | 0.3405 | 0.8608 |
92
+ | 0.3344 | 22.8571 | 80 | 0.3702 | 0.8354 |
93
+ | 0.3344 | 24.0 | 84 | 0.4352 | 0.7848 |
94
+ | 0.3344 | 24.8571 | 87 | 0.6777 | 0.7342 |
95
+ | 0.2747 | 26.0 | 91 | 0.5708 | 0.7975 |
96
+ | 0.2747 | 26.8571 | 94 | 0.4432 | 0.8101 |
97
+ | 0.2747 | 28.0 | 98 | 0.3736 | 0.8101 |
98
+ | 0.2634 | 28.8571 | 101 | 0.3938 | 0.8228 |
99
+ | 0.2634 | 30.0 | 105 | 0.4460 | 0.8354 |
100
+ | 0.2634 | 30.8571 | 108 | 0.4382 | 0.8101 |
101
+ | 0.2306 | 32.0 | 112 | 0.5574 | 0.8101 |
102
+ | 0.2306 | 32.8571 | 115 | 0.3863 | 0.8354 |
103
+ | 0.2306 | 34.0 | 119 | 0.4390 | 0.8481 |
104
+ | 0.2214 | 34.8571 | 122 | 0.4839 | 0.8481 |
105
+ | 0.2214 | 36.0 | 126 | 0.4523 | 0.8354 |
106
+ | 0.2214 | 36.8571 | 129 | 0.4022 | 0.8354 |
107
+ | 0.1945 | 38.0 | 133 | 0.4408 | 0.8354 |
108
+ | 0.1945 | 38.8571 | 136 | 0.3988 | 0.8354 |
109
+ | 0.1863 | 40.0 | 140 | 0.4467 | 0.8481 |
110
+ | 0.1863 | 40.8571 | 143 | 0.4788 | 0.8101 |
111
+ | 0.1863 | 42.0 | 147 | 0.4749 | 0.8354 |
112
+ | 0.1718 | 42.8571 | 150 | 0.4727 | 0.8228 |
113
+ | 0.1718 | 44.0 | 154 | 0.4632 | 0.8481 |
114
+ | 0.1718 | 44.8571 | 157 | 0.4561 | 0.8354 |
115
+ | 0.1535 | 46.0 | 161 | 0.5113 | 0.8101 |
116
+ | 0.1535 | 46.8571 | 164 | 0.6505 | 0.8481 |
117
+ | 0.1535 | 48.0 | 168 | 0.5612 | 0.8228 |
118
+ | 0.1454 | 48.8571 | 171 | 0.6825 | 0.8354 |
119
+ | 0.1454 | 50.0 | 175 | 0.7960 | 0.8354 |
120
+ | 0.1454 | 50.8571 | 178 | 0.5915 | 0.8228 |
121
+ | 0.1327 | 52.0 | 182 | 0.6200 | 0.8354 |
122
+ | 0.1327 | 52.8571 | 185 | 0.4977 | 0.8354 |
123
+ | 0.1327 | 54.0 | 189 | 0.6180 | 0.8608 |
124
+ | 0.1491 | 54.8571 | 192 | 0.6474 | 0.8608 |
125
+ | 0.1491 | 56.0 | 196 | 0.5886 | 0.8481 |
126
+ | 0.1491 | 56.8571 | 199 | 0.6743 | 0.8481 |
127
+ | 0.1666 | 58.0 | 203 | 0.6476 | 0.8354 |
128
+ | 0.1666 | 58.8571 | 206 | 0.6483 | 0.8481 |
129
+ | 0.1219 | 60.0 | 210 | 0.7216 | 0.8354 |
130
+ | 0.1219 | 60.8571 | 213 | 0.6541 | 0.8354 |
131
+ | 0.1219 | 62.0 | 217 | 0.6636 | 0.8354 |
132
+ | 0.1339 | 62.8571 | 220 | 0.6708 | 0.8354 |
133
+ | 0.1339 | 64.0 | 224 | 0.6735 | 0.8481 |
134
+ | 0.1339 | 64.8571 | 227 | 0.7030 | 0.8354 |
135
+ | 0.1227 | 66.0 | 231 | 0.6779 | 0.8228 |
136
+ | 0.1227 | 66.8571 | 234 | 0.7091 | 0.8354 |
137
+ | 0.1227 | 68.0 | 238 | 0.6858 | 0.8354 |
138
+ | 0.1316 | 68.8571 | 241 | 0.6668 | 0.8354 |
139
+ | 0.1316 | 70.0 | 245 | 0.6491 | 0.8354 |
140
+ | 0.1316 | 70.8571 | 248 | 0.7164 | 0.8481 |
141
+ | 0.1124 | 72.0 | 252 | 0.8063 | 0.8354 |
142
+ | 0.1124 | 72.8571 | 255 | 0.7437 | 0.8481 |
143
+ | 0.1124 | 74.0 | 259 | 0.8528 | 0.8354 |
144
+ | 0.1036 | 74.8571 | 262 | 0.9348 | 0.8101 |
145
+ | 0.1036 | 76.0 | 266 | 0.8078 | 0.8354 |
146
+ | 0.1036 | 76.8571 | 269 | 0.7697 | 0.8481 |
147
+ | 0.1057 | 78.0 | 273 | 0.8040 | 0.8481 |
148
+ | 0.1057 | 78.8571 | 276 | 0.8197 | 0.8481 |
149
+ | 0.099 | 80.0 | 280 | 0.8256 | 0.8354 |
150
+ | 0.099 | 80.8571 | 283 | 0.8057 | 0.8228 |
151
+ | 0.099 | 82.0 | 287 | 0.7797 | 0.8354 |
152
+ | 0.0927 | 82.8571 | 290 | 0.7807 | 0.8354 |
153
+ | 0.0927 | 84.0 | 294 | 0.7957 | 0.8228 |
154
+ | 0.0927 | 84.8571 | 297 | 0.8031 | 0.8228 |
155
+ | 0.0995 | 85.7143 | 300 | 0.8061 | 0.8228 |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - Transformers 4.40.2
161
+ - Pytorch 2.2.1+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:fe80b0554683dca92dfac5bfee84df96f0380bacbd3f51573674224aed7e2ae0
3
  size 343080328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8466f0d760283ae8ae49c04e4bf4db5f9c98b9079c2a6fb9c692153533ed4117
3
  size 343080328
runs/May20_12-47-55_b94dbfcd7693/events.out.tfevents.1716209276.b94dbfcd7693.1289.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:339921ea8d41e3fdfb2d02ccb5a73aea7c8f796333cd7eb0b2e00063a5fda3dc
3
- size 39377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf65a4c678a9a801d4ab43187ab90d89359282235cf225fdb6be5d26afff896
3
+ size 39731