Hugging Face's logo

hkivancoral
/
smids_3x_beit_base_sgd_001_fold1

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
b8f1a93
•
1 Parent(s): 37a8b5d

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: smids_3x_beit_base_sgd_001_fold1
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: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.34056761268781305
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
+ # smids_3x_beit_base_sgd_001_fold1
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: 1.2142
36
+ - Accuracy: 0.3406
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: 1e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 50
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 1.3018 | 1.0 | 226 | 1.3497 | 0.3088 |
69
+ | 1.233 | 2.0 | 452 | 1.3433 | 0.3105 |
70
+ | 1.2502 | 3.0 | 678 | 1.3371 | 0.3122 |
71
+ | 1.2877 | 4.0 | 904 | 1.3312 | 0.3088 |
72
+ | 1.2473 | 5.0 | 1130 | 1.3254 | 0.3072 |
73
+ | 1.2074 | 6.0 | 1356 | 1.3198 | 0.3088 |
74
+ | 1.2425 | 7.0 | 1582 | 1.3144 | 0.3088 |
75
+ | 1.2061 | 8.0 | 1808 | 1.3093 | 0.3072 |
76
+ | 1.1665 | 9.0 | 2034 | 1.3043 | 0.3105 |
77
+ | 1.2345 | 10.0 | 2260 | 1.2993 | 0.3139 |
78
+ | 1.169 | 11.0 | 2486 | 1.2948 | 0.3139 |
79
+ | 1.1772 | 12.0 | 2712 | 1.2903 | 0.3139 |
80
+ | 1.2448 | 13.0 | 2938 | 1.2861 | 0.3172 |
81
+ | 1.1958 | 14.0 | 3164 | 1.2819 | 0.3205 |
82
+ | 1.1284 | 15.0 | 3390 | 1.2779 | 0.3222 |
83
+ | 1.1355 | 16.0 | 3616 | 1.2740 | 0.3222 |
84
+ | 1.1754 | 17.0 | 3842 | 1.2702 | 0.3222 |
85
+ | 1.1535 | 18.0 | 4068 | 1.2665 | 0.3239 |
86
+ | 1.1762 | 19.0 | 4294 | 1.2631 | 0.3255 |
87
+ | 1.2186 | 20.0 | 4520 | 1.2598 | 0.3255 |
88
+ | 1.1196 | 21.0 | 4746 | 1.2566 | 0.3272 |
89
+ | 1.1702 | 22.0 | 4972 | 1.2535 | 0.3255 |
90
+ | 1.1389 | 23.0 | 5198 | 1.2506 | 0.3255 |
91
+ | 1.1587 | 24.0 | 5424 | 1.2478 | 0.3289 |
92
+ | 1.1561 | 25.0 | 5650 | 1.2450 | 0.3306 |
93
+ | 1.1709 | 26.0 | 5876 | 1.2425 | 0.3322 |
94
+ | 1.1654 | 27.0 | 6102 | 1.2400 | 0.3322 |
95
+ | 1.1373 | 28.0 | 6328 | 1.2376 | 0.3339 |
96
+ | 1.1306 | 29.0 | 6554 | 1.2354 | 0.3339 |
97
+ | 1.1454 | 30.0 | 6780 | 1.2333 | 0.3356 |
98
+ | 1.1141 | 31.0 | 7006 | 1.2313 | 0.3322 |
99
+ | 1.1582 | 32.0 | 7232 | 1.2295 | 0.3339 |
100
+ | 1.1347 | 33.0 | 7458 | 1.2277 | 0.3339 |
101
+ | 1.1265 | 34.0 | 7684 | 1.2261 | 0.3356 |
102
+ | 1.1205 | 35.0 | 7910 | 1.2245 | 0.3356 |
103
+ | 1.122 | 36.0 | 8136 | 1.2231 | 0.3356 |
104
+ | 1.1483 | 37.0 | 8362 | 1.2218 | 0.3372 |
105
+ | 1.1233 | 38.0 | 8588 | 1.2206 | 0.3389 |
106
+ | 1.1213 | 39.0 | 8814 | 1.2195 | 0.3389 |
107
+ | 1.0703 | 40.0 | 9040 | 1.2185 | 0.3389 |
108
+ | 1.1268 | 41.0 | 9266 | 1.2176 | 0.3389 |
109
+ | 1.082 | 42.0 | 9492 | 1.2169 | 0.3406 |
110
+ | 1.0999 | 43.0 | 9718 | 1.2162 | 0.3406 |
111
+ | 1.1354 | 44.0 | 9944 | 1.2156 | 0.3406 |
112
+ | 1.1066 | 45.0 | 10170 | 1.2151 | 0.3406 |
113
+ | 1.1669 | 46.0 | 10396 | 1.2148 | 0.3406 |
114
+ | 1.1433 | 47.0 | 10622 | 1.2145 | 0.3406 |
115
+ | 1.1581 | 48.0 | 10848 | 1.2143 | 0.3406 |
116
+ | 1.1184 | 49.0 | 11074 | 1.2142 | 0.3406 |
117
+ | 1.1092 | 50.0 | 11300 | 1.2142 | 0.3406 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88fd4881cf157f57278b45db24cf9d9a79f51f0d6af850f2bf2f1ed434f65b76
3
  size 343133766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0860c155ba58f4c6b6cef00d4dda9356b86171ed15869c9e79716b2b9c5fa33
3
  size 343133766