stbnlen commited on
Commit
0e36d92
·
1 Parent(s): 3b29d6a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -7,7 +7,7 @@ datasets:
7
  metrics:
8
  - accuracy
9
  model-index:
10
- - name: Pokemon Classifier
11
  results:
12
  - task:
13
  name: Image Classification
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.09496402877697842
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the pokemon-classification dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 8.0010
35
- - Accuracy: 0.0950
36
 
37
  ## Model description
38
 
@@ -63,10 +63,10 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 1.3716 | 0.82 | 500 | 7.1987 | 0.0655 |
67
- | 0.1136 | 1.64 | 1000 | 7.6050 | 0.0777 |
68
- | 0.0434 | 2.46 | 1500 | 8.0010 | 0.0820 |
69
- | 0.0163 | 3.28 | 2000 | 8.0010 | 0.0950 |
70
 
71
 
72
  ### Framework versions
 
7
  metrics:
8
  - accuracy
9
  model-index:
10
+ - name: pokemon_classifier
11
  results:
12
  - task:
13
  name: Image Classification
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.08848920863309352
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](https://huggingface.co/google/vit-base-patch16-224) on the pokemon-classification dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 8.0935
35
+ - Accuracy: 0.0885
36
 
37
  ## Model description
38
 
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 2.0872 | 0.82 | 500 | 7.2669 | 0.0640 |
67
+ | 0.1581 | 1.64 | 1000 | 7.6072 | 0.0712 |
68
+ | 0.0536 | 2.46 | 1500 | 7.8952 | 0.0842 |
69
+ | 0.0169 | 3.28 | 2000 | 8.0935 | 0.0885 |
70
 
71
 
72
  ### Framework versions