nielsr HF staff commited on
Commit
6831d3c
1 Parent(s): 1d985b0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
- - cifar10
7
  metrics:
8
  - accuracy
9
  model-index:
@@ -13,13 +13,13 @@ model-index:
13
  name: Image Classification
14
  type: image-classification
15
  dataset:
16
- name: cifar10
17
- type: cifar10
18
- args: plain_text
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9855
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # vit-base-patch16-224-in21k-finetuned-cifar10
29
 
30
- 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.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.1011
33
- - Accuracy: 0.9855
34
 
35
  ## Model description
36
 
@@ -64,14 +64,14 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 0.3831 | 1.0 | 390 | 0.2057 | 0.978 |
68
- | 0.3007 | 2.0 | 780 | 0.1199 | 0.9845 |
69
- | 0.2442 | 3.0 | 1170 | 0.1011 | 0.9855 |
70
 
71
 
72
  ### Framework versions
73
 
74
- - Transformers 4.16.2
75
  - Pytorch 1.10.0+cu111
76
- - Datasets 1.18.3
77
- - Tokenizers 0.11.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
+ - image_folder
7
  metrics:
8
  - accuracy
9
  model-index:
13
  name: Image Classification
14
  type: image-classification
15
  dataset:
16
+ name: image_folder
17
+ type: image_folder
18
+ args: default
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9881481481481481
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
 
28
  # vit-base-patch16-224-in21k-finetuned-cifar10
29
 
30
+ 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 image_folder dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.1357
33
+ - Accuracy: 0.9881
34
 
35
  ## Model description
36
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.2455 | 1.0 | 190 | 0.2227 | 0.9830 |
68
+ | 0.1363 | 2.0 | 380 | 0.1357 | 0.9881 |
69
+ | 0.0954 | 3.0 | 570 | 0.1194 | 0.9878 |
70
 
71
 
72
  ### Framework versions
73
 
74
+ - Transformers 4.18.0
75
  - Pytorch 1.10.0+cu111
76
+ - Datasets 2.0.0
77
+ - Tokenizers 0.11.6