Hugging Face's logo

matthieulel
/
dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist

Image Classification
Safetensors
dinov2
vision
Generated from Trainer
Model card Files
xet
Community
matthieulel commited on
Commit
3342963
·
verified ·
1 Parent(s): eae72ba

Model save

Browse files
Files changed (2) hide show
  1. README.md +37 -39
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/dinov2-base-imagenet1k-1-layer
4
  tags:
5
- - image-classification
6
- - vision
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
@@ -20,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  # dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist
22
 
23
- This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on the matthieulel/galaxy_mnist dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.2800
26
- - Accuracy: 0.93
27
- - Precision: 0.9301
28
- - Recall: 0.93
29
- - F1: 0.9300
30
 
31
  ## Model description
32
 
@@ -45,7 +43,7 @@ More information needed
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
48
- - learning_rate: 5e-05
49
  - train_batch_size: 64
50
  - eval_batch_size: 64
51
  - seed: 42
@@ -60,36 +58,36 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
- | 0.4569 | 0.99 | 31 | 0.4350 | 0.8145 | 0.8694 | 0.8145 | 0.8062 |
64
- | 0.4173 | 1.98 | 62 | 0.3161 | 0.871 | 0.8848 | 0.871 | 0.8682 |
65
- | 0.4318 | 2.98 | 93 | 0.3914 | 0.8285 | 0.8801 | 0.8285 | 0.8216 |
66
- | 0.4238 | 4.0 | 125 | 0.3689 | 0.8485 | 0.8684 | 0.8485 | 0.8441 |
67
- | 0.3735 | 4.99 | 156 | 0.2969 | 0.8735 | 0.8929 | 0.8735 | 0.8705 |
68
- | 0.3371 | 5.98 | 187 | 0.2174 | 0.906 | 0.9136 | 0.906 | 0.9063 |
69
- | 0.3069 | 6.98 | 218 | 0.2422 | 0.9055 | 0.9077 | 0.9055 | 0.9049 |
70
- | 0.2526 | 8.0 | 250 | 0.2783 | 0.8905 | 0.9072 | 0.8905 | 0.8899 |
71
- | 0.2753 | 8.99 | 281 | 0.2373 | 0.9155 | 0.9176 | 0.9155 | 0.9150 |
72
- | 0.2704 | 9.98 | 312 | 0.2804 | 0.8865 | 0.9001 | 0.8865 | 0.8864 |
73
- | 0.2417 | 10.98 | 343 | 0.2078 | 0.912 | 0.9126 | 0.912 | 0.9122 |
74
- | 0.266 | 12.0 | 375 | 0.2004 | 0.918 | 0.9188 | 0.918 | 0.9183 |
75
- | 0.2387 | 12.99 | 406 | 0.2255 | 0.9165 | 0.9196 | 0.9165 | 0.9160 |
76
- | 0.2137 | 13.98 | 437 | 0.2208 | 0.9145 | 0.9169 | 0.9145 | 0.9147 |
77
- | 0.2063 | 14.98 | 468 | 0.2078 | 0.9205 | 0.9210 | 0.9205 | 0.9204 |
78
- | 0.2081 | 16.0 | 500 | 0.2658 | 0.9045 | 0.9115 | 0.9045 | 0.9037 |
79
- | 0.1862 | 16.99 | 531 | 0.2425 | 0.914 | 0.9208 | 0.914 | 0.9143 |
80
- | 0.1905 | 17.98 | 562 | 0.2398 | 0.912 | 0.9114 | 0.912 | 0.9116 |
81
- | 0.1727 | 18.98 | 593 | 0.2999 | 0.9085 | 0.9100 | 0.9085 | 0.9084 |
82
- | 0.1697 | 20.0 | 625 | 0.2520 | 0.9185 | 0.9197 | 0.9185 | 0.9183 |
83
- | 0.161 | 20.99 | 656 | 0.2471 | 0.9205 | 0.9216 | 0.9205 | 0.9205 |
84
- | 0.1363 | 21.98 | 687 | 0.2449 | 0.922 | 0.9224 | 0.922 | 0.9222 |
85
- | 0.1533 | 22.98 | 718 | 0.2780 | 0.917 | 0.9179 | 0.917 | 0.9173 |
86
- | 0.1324 | 24.0 | 750 | 0.2683 | 0.917 | 0.9184 | 0.917 | 0.9170 |
87
- | 0.1291 | 24.99 | 781 | 0.2651 | 0.924 | 0.9243 | 0.924 | 0.9240 |
88
- | 0.1112 | 25.98 | 812 | 0.3036 | 0.924 | 0.9245 | 0.924 | 0.9240 |
89
- | 0.1175 | 26.98 | 843 | 0.2818 | 0.927 | 0.9270 | 0.927 | 0.9269 |
90
- | 0.1214 | 28.0 | 875 | 0.2800 | 0.93 | 0.9301 | 0.93 | 0.9300 |
91
- | 0.0953 | 28.99 | 906 | 0.3168 | 0.9245 | 0.9244 | 0.9245 | 0.9244 |
92
- | 0.0955 | 29.76 | 930 | 0.3216 | 0.925 | 0.9249 | 0.925 | 0.9249 |
93
 
94
 
95
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: facebook/dinov2-base-imagenet1k-1-layer
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
18
 
19
  # dinov2-base-imagenet1k-1-layer-finetuned-galaxy_mnist
20
 
21
+ This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2004
24
+ - Accuracy: 0.931
25
+ - Precision: 0.9310
26
+ - Recall: 0.931
27
+ - F1: 0.9310
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 5e-06
47
  - train_batch_size: 64
48
  - eval_batch_size: 64
49
  - seed: 42
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
+ | 0.8401 | 0.99 | 31 | 0.6220 | 0.7605 | 0.7579 | 0.7605 | 0.7543 |
62
+ | 0.3857 | 1.98 | 62 | 0.2696 | 0.8875 | 0.8881 | 0.8875 | 0.8877 |
63
+ | 0.3144 | 2.98 | 93 | 0.2491 | 0.9015 | 0.9028 | 0.9015 | 0.9010 |
64
+ | 0.2769 | 4.0 | 125 | 0.2179 | 0.913 | 0.9129 | 0.913 | 0.9128 |
65
+ | 0.2858 | 4.99 | 156 | 0.2455 | 0.9025 | 0.9070 | 0.9025 | 0.9020 |
66
+ | 0.2704 | 5.98 | 187 | 0.2121 | 0.9155 | 0.9234 | 0.9155 | 0.9156 |
67
+ | 0.2557 | 6.98 | 218 | 0.2177 | 0.9155 | 0.9190 | 0.9155 | 0.9152 |
68
+ | 0.2069 | 8.0 | 250 | 0.1864 | 0.9255 | 0.9256 | 0.9255 | 0.9255 |
69
+ | 0.2344 | 8.99 | 281 | 0.1894 | 0.923 | 0.9237 | 0.923 | 0.9230 |
70
+ | 0.1996 | 9.98 | 312 | 0.1993 | 0.9235 | 0.9260 | 0.9235 | 0.9234 |
71
+ | 0.2011 | 10.98 | 343 | 0.1828 | 0.928 | 0.9280 | 0.928 | 0.9279 |
72
+ | 0.2229 | 12.0 | 375 | 0.2358 | 0.9155 | 0.9233 | 0.9155 | 0.9145 |
73
+ | 0.1792 | 12.99 | 406 | 0.1897 | 0.9205 | 0.9214 | 0.9205 | 0.9205 |
74
+ | 0.1898 | 13.98 | 437 | 0.2017 | 0.921 | 0.9217 | 0.921 | 0.9208 |
75
+ | 0.1735 | 14.98 | 468 | 0.1954 | 0.927 | 0.9270 | 0.927 | 0.9269 |
76
+ | 0.1751 | 16.0 | 500 | 0.1918 | 0.9295 | 0.9299 | 0.9295 | 0.9294 |
77
+ | 0.1732 | 16.99 | 531 | 0.1906 | 0.922 | 0.9225 | 0.922 | 0.9219 |
78
+ | 0.1738 | 17.98 | 562 | 0.1846 | 0.931 | 0.9317 | 0.931 | 0.9310 |
79
+ | 0.1694 | 18.98 | 593 | 0.1875 | 0.9365 | 0.9367 | 0.9365 | 0.9365 |
80
+ | 0.1723 | 20.0 | 625 | 0.1941 | 0.9285 | 0.9293 | 0.9285 | 0.9284 |
81
+ | 0.1574 | 20.99 | 656 | 0.1905 | 0.9335 | 0.9337 | 0.9335 | 0.9336 |
82
+ | 0.1485 | 21.98 | 687 | 0.1869 | 0.9315 | 0.9313 | 0.9315 | 0.9314 |
83
+ | 0.1537 | 22.98 | 718 | 0.1830 | 0.936 | 0.9360 | 0.936 | 0.9360 |
84
+ | 0.1406 | 24.0 | 750 | 0.1975 | 0.932 | 0.9322 | 0.932 | 0.9320 |
85
+ | 0.1326 | 24.99 | 781 | 0.1918 | 0.9315 | 0.9316 | 0.9315 | 0.9315 |
86
+ | 0.1238 | 25.98 | 812 | 0.2105 | 0.9275 | 0.9288 | 0.9275 | 0.9276 |
87
+ | 0.1299 | 26.98 | 843 | 0.2022 | 0.9325 | 0.9327 | 0.9325 | 0.9324 |
88
+ | 0.1387 | 28.0 | 875 | 0.2011 | 0.9335 | 0.9337 | 0.9335 | 0.9336 |
89
+ | 0.1279 | 28.99 | 906 | 0.2005 | 0.931 | 0.9310 | 0.931 | 0.9310 |
90
+ | 0.1256 | 29.76 | 930 | 0.2004 | 0.931 | 0.9310 | 0.931 | 0.9310 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36c5a0908180461f63147fc01883904115b10df370c77aca1b0dd313accb9546
3
  size 346372224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83207eddde032e024d40e07572f4cb2198ec2b2a03eb9ab898073d31d1e6b22a
3
  size 346372224