Hugging Face's logo

frncscp
/
dinotron

Image Classification
Transformers
PyTorch
dinov2
Generated from Trainer
Inference Endpoints
Model card Files Community
1
frncscp commited on
Commit
3da4c6a
·
1 Parent(s): dc713a3

End of training

Browse files
Files changed (2) hide show
  1. README.md +112 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/dinov2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: Dinotron
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Dinotron
17
+
18
+ This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0265
21
+ - Accuracy: 0.9932
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 50
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 1.0 | 7 | 0.1146 | 0.9638 |
56
+ | 0.3773 | 2.0 | 14 | 0.0336 | 0.9932 |
57
+ | 0.0541 | 3.0 | 21 | 0.0402 | 0.9887 |
58
+ | 0.0541 | 4.0 | 28 | 0.0463 | 0.9887 |
59
+ | 0.0476 | 5.0 | 35 | 0.0594 | 0.9819 |
60
+ | 0.1408 | 6.0 | 42 | 0.1296 | 0.9570 |
61
+ | 0.1408 | 7.0 | 49 | 0.0872 | 0.9729 |
62
+ | 0.0898 | 8.0 | 56 | 0.2245 | 0.9344 |
63
+ | 0.216 | 9.0 | 63 | 0.1444 | 0.9570 |
64
+ | 0.076 | 10.0 | 70 | 0.0316 | 0.9887 |
65
+ | 0.076 | 11.0 | 77 | 0.0411 | 0.9864 |
66
+ | 0.0369 | 12.0 | 84 | 0.0275 | 0.9887 |
67
+ | 0.0505 | 13.0 | 91 | 0.1610 | 0.9638 |
68
+ | 0.0505 | 14.0 | 98 | 0.0513 | 0.9910 |
69
+ | 0.0274 | 15.0 | 105 | 0.2366 | 0.9615 |
70
+ | 0.0735 | 16.0 | 112 | 0.0738 | 0.9796 |
71
+ | 0.0735 | 17.0 | 119 | 0.0529 | 0.9819 |
72
+ | 0.0334 | 18.0 | 126 | 0.1024 | 0.9661 |
73
+ | 0.0347 | 19.0 | 133 | 0.0919 | 0.9819 |
74
+ | 0.0206 | 20.0 | 140 | 0.0851 | 0.9864 |
75
+ | 0.0206 | 21.0 | 147 | 0.1004 | 0.9796 |
76
+ | 0.0516 | 22.0 | 154 | 0.1706 | 0.9638 |
77
+ | 0.0418 | 23.0 | 161 | 0.0505 | 0.9910 |
78
+ | 0.0418 | 24.0 | 168 | 0.0939 | 0.9774 |
79
+ | 0.0173 | 25.0 | 175 | 0.0553 | 0.9842 |
80
+ | 0.0239 | 26.0 | 182 | 0.1255 | 0.9796 |
81
+ | 0.0239 | 27.0 | 189 | 0.2256 | 0.9661 |
82
+ | 0.0286 | 28.0 | 196 | 0.0943 | 0.9751 |
83
+ | 0.0502 | 29.0 | 203 | 0.0937 | 0.9751 |
84
+ | 0.0102 | 30.0 | 210 | 0.0910 | 0.9842 |
85
+ | 0.0102 | 31.0 | 217 | 0.0336 | 0.9887 |
86
+ | 0.0182 | 32.0 | 224 | 0.0870 | 0.9796 |
87
+ | 0.0126 | 33.0 | 231 | 0.0565 | 0.9842 |
88
+ | 0.0126 | 34.0 | 238 | 0.0541 | 0.9842 |
89
+ | 0.0157 | 35.0 | 245 | 0.0591 | 0.9932 |
90
+ | 0.0059 | 36.0 | 252 | 0.0985 | 0.9819 |
91
+ | 0.0059 | 37.0 | 259 | 0.0813 | 0.9819 |
92
+ | 0.0092 | 38.0 | 266 | 0.0239 | 0.9955 |
93
+ | 0.0225 | 39.0 | 273 | 0.0982 | 0.9706 |
94
+ | 0.0105 | 40.0 | 280 | 0.0113 | 0.9955 |
95
+ | 0.0105 | 41.0 | 287 | 0.0127 | 0.9977 |
96
+ | 0.007 | 42.0 | 294 | 0.0760 | 0.9887 |
97
+ | 0.0032 | 43.0 | 301 | 0.0196 | 0.9932 |
98
+ | 0.0032 | 44.0 | 308 | 0.0171 | 0.9932 |
99
+ | 0.0206 | 45.0 | 315 | 0.0501 | 0.9910 |
100
+ | 0.0001 | 46.0 | 322 | 0.0925 | 0.9842 |
101
+ | 0.0001 | 47.0 | 329 | 0.0318 | 0.9910 |
102
+ | 0.0017 | 48.0 | 336 | 0.0612 | 0.9864 |
103
+ | 0.0023 | 49.0 | 343 | 0.0685 | 0.9864 |
104
+ | 0.0013 | 50.0 | 350 | 0.0265 | 0.9932 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.33.3
110
+ - Pytorch 2.0.1+cu118
111
+ - Datasets 2.14.5
112
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dfd0235949565675e791467d9ddec3864c82153b2f7dbc2bc4079f96b6b25af
3
  size 346410257
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2374a0caa40a02f60bb643c5a200c8de765e7f5ede456702f38a2e5a275db1c2
3
  size 346410257