pkr7098 commited on
Commit
c1af32c
1 Parent(s): 2af597c

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -16
README.md CHANGED
@@ -1,13 +1,11 @@
1
  ---
2
- library_name: transformers
3
- license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
- tags:
6
- - image-classification
7
- - vision
8
- - generated_from_trainer
9
  metrics:
10
  - accuracy
 
 
11
  model-index:
12
  - name: vit-cifar100-cifar100
13
  results: []
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # vit-cifar100-cifar100
20
 
21
- 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 cifar100 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.2851
24
- - Accuracy: 0.9252
25
 
26
  ## Model description
27
 
@@ -40,7 +38,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 3e-05
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 1337
@@ -52,16 +50,17 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
- | 1.0634 | 1.0 | 5313 | 0.7235 | 0.8777 |
56
- | 0.7839 | 2.0 | 10626 | 0.3731 | 0.9056 |
57
- | 0.5749 | 3.0 | 15939 | 0.3214 | 0.9153 |
58
- | 0.3432 | 4.0 | 21252 | 0.2990 | 0.9209 |
59
- | 0.4763 | 5.0 | 26565 | 0.2851 | 0.9252 |
60
 
61
 
62
  ### Framework versions
63
 
 
64
  - Transformers 4.44.2
65
  - Pytorch 2.0.1+cu117
66
  - Datasets 3.0.0
67
- - Tokenizers 0.19.1
 
1
  ---
 
 
2
  base_model: google/vit-base-patch16-224-in21k
3
+ library_name: peft
4
+ license: apache-2.0
 
 
5
  metrics:
6
  - accuracy
7
+ tags:
8
+ - generated_from_trainer
9
  model-index:
10
  - name: vit-cifar100-cifar100
11
  results: []
 
16
 
17
  # vit-cifar100-cifar100
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: 0.2550
22
+ - Accuracy: 0.9236
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.0005
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 1337
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 0.5206 | 1.0 | 5313 | 0.3323 | 0.9051 |
54
+ | 0.7608 | 2.0 | 10626 | 0.2929 | 0.9139 |
55
+ | 0.8691 | 3.0 | 15939 | 0.2725 | 0.9173 |
56
+ | 0.3582 | 4.0 | 21252 | 0.2581 | 0.9232 |
57
+ | 0.4711 | 5.0 | 26565 | 0.2550 | 0.9236 |
58
 
59
 
60
  ### Framework versions
61
 
62
+ - PEFT 0.12.0
63
  - Transformers 4.44.2
64
  - Pytorch 2.0.1+cu117
65
  - Datasets 3.0.0
66
+ - Tokenizers 0.19.1