Hugging Face's logo

simlaharma
/
vit-base-cifar10

Image Classification
Transformers
PyTorch
vit
vision
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
simlaharma commited on
Commit
6efa302
·
1 Parent(s): d4d674c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -15
README.md CHANGED
@@ -1,8 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - image-classification
5
- - vision
6
  - generated_from_trainer
7
  datasets:
8
  - cifar10
@@ -23,7 +21,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9869333333333333
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  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 cifar10 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.0468
37
- - Accuracy: 0.9869
38
 
39
  ## Model description
40
 
@@ -67,16 +65,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.4169 | 1.0 | 664 | 0.1741 | 0.9725 |
71
- | 0.3364 | 2.0 | 1328 | 0.1108 | 0.9745 |
72
- | 0.2856 | 3.0 | 1992 | 0.0864 | 0.9764 |
73
- | 0.2716 | 4.0 | 2656 | 0.0721 | 0.9811 |
74
- | 0.2738 | 5.0 | 3320 | 0.0678 | 0.9824 |
75
- | 0.2432 | 6.0 | 3984 | 0.0610 | 0.9825 |
76
- | 0.2163 | 7.0 | 4648 | 0.0603 | 0.9843 |
77
- | 0.2368 | 8.0 | 5312 | 0.0580 | 0.9835 |
78
- | 0.2236 | 9.0 | 5976 | 0.0506 | 0.9855 |
79
- | 0.1671 | 10.0 | 6640 | 0.0496 | 0.9856 |
80
 
81
 
82
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
 
4
  - generated_from_trainer
5
  datasets:
6
  - cifar10
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.10253333333333334
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  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 cifar10 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 2.3473
35
+ - Accuracy: 0.1025
36
 
37
  ## Model description
38
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.3324 | 1.0 | 664 | 2.3352 | 0.0967 |
69
+ | 2.3489 | 2.0 | 1328 | 2.3288 | 0.1049 |
70
+ | 2.4899 | 3.0 | 1992 | 2.4473 | 0.0989 |
71
+ | 2.479 | 4.0 | 2656 | 2.4894 | 0.1 |
72
+ | 2.4179 | 5.0 | 3320 | 2.4404 | 0.0947 |
73
+ | 2.3881 | 6.0 | 3984 | 2.3931 | 0.102 |
74
+ | 2.3597 | 7.0 | 4648 | 2.3744 | 0.0967 |
75
+ | 2.3721 | 8.0 | 5312 | 2.3667 | 0.0935 |
76
+ | 2.3456 | 9.0 | 5976 | 2.3495 | 0.1036 |
77
+ | 2.3361 | 10.0 | 6640 | 2.3473 | 0.1025 |
78
 
79
 
80
  ### Framework versions