Hugging Face's logo

mbiarreta
/
vit-ena24

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
Metrics Community
mbiarreta commited on
Commit
1808f75
·
verified ·
1 Parent(s): f50e5ad

Model save

Browse files
Files changed (2) hide show
  1. README.md +20 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,7 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
- - image-classification
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
@@ -17,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # vit-ena24
19
 
20
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ena24 dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1241
23
- - Accuracy: 0.9710
24
 
25
  ## Model description
26
 
@@ -52,26 +51,26 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 1.9499 | 0.1302 | 100 | 1.7695 | 0.5885 |
56
- | 1.2926 | 0.2604 | 200 | 1.1301 | 0.7389 |
57
- | 0.8506 | 0.3906 | 300 | 0.8700 | 0.7786 |
58
- | 0.6715 | 0.5208 | 400 | 0.7060 | 0.8397 |
59
- | 0.5668 | 0.6510 | 500 | 0.5341 | 0.8603 |
60
- | 0.5531 | 0.7812 | 600 | 0.4424 | 0.8893 |
61
- | 0.2316 | 0.9115 | 700 | 0.3669 | 0.9 |
62
- | 0.2114 | 1.0417 | 800 | 0.2665 | 0.9374 |
63
- | 0.1614 | 1.1719 | 900 | 0.2684 | 0.9359 |
64
- | 0.1441 | 1.3021 | 1000 | 0.2139 | 0.9504 |
65
- | 0.1 | 1.4323 | 1100 | 0.1795 | 0.9603 |
66
- | 0.1394 | 1.5625 | 1200 | 0.1471 | 0.9672 |
67
- | 0.067 | 1.6927 | 1300 | 0.1412 | 0.9687 |
68
- | 0.15 | 1.8229 | 1400 | 0.1329 | 0.9695 |
69
- | 0.0848 | 1.9531 | 1500 | 0.1241 | 0.9710 |
70
 
71
 
72
  ### Framework versions
73
 
74
- - Transformers 4.50.2
75
  - Pytorch 2.6.0+cu124
76
- - Datasets 3.5.0
77
  - Tokenizers 0.21.1
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # vit-ena24
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.3273
22
+ - Accuracy: 0.7539
23
 
24
  ## Model description
25
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 1.5119 | 0.1259 | 100 | 1.8353 | 0.5625 |
55
+ | 0.809 | 0.2519 | 200 | 1.4106 | 0.6396 |
56
+ | 0.6754 | 0.3778 | 300 | 1.5657 | 0.5771 |
57
+ | 0.5017 | 0.5038 | 400 | 1.3136 | 0.6865 |
58
+ | 0.2595 | 0.6297 | 500 | 1.2942 | 0.6865 |
59
+ | 0.243 | 0.7557 | 600 | 1.3563 | 0.6914 |
60
+ | 0.3432 | 0.8816 | 700 | 1.4268 | 0.6689 |
61
+ | 0.1115 | 1.0076 | 800 | 1.4286 | 0.6973 |
62
+ | 0.1615 | 1.1335 | 900 | 1.4697 | 0.6963 |
63
+ | 0.115 | 1.2594 | 1000 | 1.4701 | 0.7109 |
64
+ | 0.0656 | 1.3854 | 1100 | 1.4417 | 0.7217 |
65
+ | 0.1229 | 1.5113 | 1200 | 1.3150 | 0.7451 |
66
+ | 0.1064 | 1.6373 | 1300 | 1.3941 | 0.7432 |
67
+ | 0.0345 | 1.7632 | 1400 | 1.2879 | 0.7607 |
68
+ | 0.0587 | 1.8892 | 1500 | 1.3273 | 0.7539 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.51.3
74
  - Pytorch 2.6.0+cu124
75
+ - Datasets 3.6.0
76
  - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00a76d8a11d45594b022ad1a612099b0926048987f9bc8fa4a4852732038c1ae
3
  size 343282420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427bc9224abf1a15f2f72df0152cbe26b0a34e2c672152971bd8741b81561920
3
  size 343282420