Hugging Face's logo

matthieulel
/
dinov2-small-imagenet1k-1-layer-finetuned-galaxy10-decals

Image Classification
Transformers
TensorBoard
Safetensors
dinov2
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
matthieulel commited on
Commit
5d0400b
·
verified ·
1 Parent(s): 44c9f03

Model save

Browse files
Files changed (2) hide show
  1. README.md +25 -27
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/dinov2-small-imagenet1k-1-layer
4
  tags:
5
- - image-classification
6
- - vision
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # dinov2-small-imagenet1k-1-layer-finetuned-galaxy10-decals
19
 
20
- This model is a fine-tuned version of [facebook/dinov2-small-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-small-imagenet1k-1-layer) on the matthieulel/galaxy10_decals dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.0579
23
- - Accuracy: 0.6387
24
 
25
  ## Model description
26
 
@@ -39,7 +37,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 1e-07
43
  - train_batch_size: 32
44
  - eval_batch_size: 32
45
  - seed: 42
@@ -54,31 +52,31 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
- | 3.2794 | 0.9940 | 124 | 3.2713 | 0.0924 |
58
- | 2.2032 | 1.9960 | 249 | 2.1443 | 0.2401 |
59
- | 1.9114 | 2.9980 | 374 | 1.8624 | 0.3777 |
60
- | 1.6905 | 4.0 | 499 | 1.6865 | 0.4453 |
61
- | 1.5548 | 4.9940 | 623 | 1.5515 | 0.4853 |
62
- | 1.4678 | 5.9960 | 748 | 1.4546 | 0.5068 |
63
- | 1.3977 | 6.9980 | 873 | 1.3747 | 0.5372 |
64
- | 1.3531 | 8.0 | 998 | 1.3144 | 0.5536 |
65
- | 1.3098 | 8.9940 | 1122 | 1.2655 | 0.5660 |
66
- | 1.2152 | 9.9960 | 1247 | 1.2197 | 0.5817 |
67
- | 1.2257 | 10.9980 | 1372 | 1.1856 | 0.5924 |
68
- | 1.1706 | 12.0 | 1497 | 1.1540 | 0.6082 |
69
- | 1.1836 | 12.9940 | 1621 | 1.1286 | 0.6122 |
70
- | 1.1769 | 13.9960 | 1746 | 1.1120 | 0.6161 |
71
- | 1.1197 | 14.9980 | 1871 | 1.0943 | 0.6234 |
72
- | 1.1373 | 16.0 | 1996 | 1.0772 | 0.6308 |
73
- | 1.1111 | 16.9940 | 2120 | 1.0714 | 0.6330 |
74
- | 1.1274 | 17.9960 | 2245 | 1.0624 | 0.6336 |
75
- | 1.0801 | 18.9980 | 2370 | 1.0584 | 0.6381 |
76
- | 1.0979 | 19.8798 | 2480 | 1.0579 | 0.6387 |
77
 
78
 
79
  ### Framework versions
80
 
81
  - Transformers 4.40.1
82
- - Pytorch 2.1.1+cu121
83
  - Datasets 2.19.1
84
  - Tokenizers 0.19.1
 
2
  license: apache-2.0
3
  base_model: facebook/dinov2-small-imagenet1k-1-layer
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
15
 
16
  # dinov2-small-imagenet1k-1-layer-finetuned-galaxy10-decals
17
 
18
+ This model is a fine-tuned version of [facebook/dinov2-small-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-small-imagenet1k-1-layer) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4505
21
+ - Accuracy: 0.8664
22
 
23
  ## Model description
24
 
 
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
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
+ | 0.924 | 0.9940 | 124 | 0.8075 | 0.7294 |
56
+ | 0.8226 | 1.9960 | 249 | 0.8195 | 0.7193 |
57
+ | 0.805 | 2.9980 | 374 | 0.6233 | 0.7903 |
58
+ | 0.752 | 4.0 | 499 | 0.6687 | 0.7796 |
59
+ | 0.6193 | 4.9940 | 623 | 0.5708 | 0.8050 |
60
+ | 0.5822 | 5.9960 | 748 | 0.5624 | 0.8061 |
61
+ | 0.6227 | 6.9980 | 873 | 0.5536 | 0.8134 |
62
+ | 0.6067 | 8.0 | 998 | 0.5687 | 0.8185 |
63
+ | 0.533 | 8.9940 | 1122 | 0.5919 | 0.8089 |
64
+ | 0.5423 | 9.9960 | 1247 | 0.5022 | 0.8371 |
65
+ | 0.4747 | 10.9980 | 1372 | 0.4419 | 0.8579 |
66
+ | 0.4367 | 12.0 | 1497 | 0.5084 | 0.8207 |
67
+ | 0.4907 | 12.9940 | 1621 | 0.4774 | 0.8365 |
68
+ | 0.4269 | 13.9960 | 1746 | 0.4945 | 0.8444 |
69
+ | 0.3787 | 14.9980 | 1871 | 0.4779 | 0.8478 |
70
+ | 0.3724 | 16.0 | 1996 | 0.4242 | 0.8715 |
71
+ | 0.354 | 16.9940 | 2120 | 0.4595 | 0.8529 |
72
+ | 0.3304 | 17.9960 | 2245 | 0.4543 | 0.8563 |
73
+ | 0.2849 | 18.9980 | 2370 | 0.4699 | 0.8608 |
74
+ | 0.2456 | 19.8798 | 2480 | 0.4505 | 0.8664 |
75
 
76
 
77
  ### Framework versions
78
 
79
  - Transformers 4.40.1
80
+ - Pytorch 2.2.1+cu121
81
  - Datasets 2.19.1
82
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b91ffcbb410ddde6ad2a45c99a9cc5abe05f90350ea16821d3b2074a1a9d3e7d
3
  size 88282440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44a1220acf7c6871a74bbab1aadbb87ae8b271a183b16b847b95db192e3ea73
3
  size 88282440