Hugging Face's logo

crasyangel
/
my_awesome_food_model

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Model card Files Community
1
crasyangel commited on
Commit
8d563b9
·
1 Parent(s): 65cdb6c

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -4,7 +4,7 @@ base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - food101
8
  metrics:
9
  - accuracy
10
  model-index:
@@ -14,11 +14,11 @@ model-index:
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
- name: food101
18
- type: food101
19
- config: default
20
- split: train[:5000]
21
- args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
@@ -30,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # my_awesome_food_model
32
 
33
- 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 food101 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.9566
36
  - Accuracy: 0.921
37
 
38
  ## Model description
@@ -67,9 +67,9 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.3043 | 0.99 | 62 | 1.2840 | 0.91 |
71
- | 1.0293 | 2.0 | 125 | 1.0594 | 0.902 |
72
- | 0.9053 | 2.98 | 186 | 0.9566 | 0.921 |
73
 
74
 
75
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - cifar10
8
  metrics:
9
  - accuracy
10
  model-index:
 
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
+ name: cifar10
18
+ type: cifar10
19
+ config: plain_text
20
+ split: train[:50000]
21
+ args: plain_text
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
 
30
 
31
  # my_awesome_food_model
32
 
33
+ 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.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2768
36
  - Accuracy: 0.921
37
 
38
  ## Model description
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.4414 | 1.0 | 625 | 0.4034 | 0.9011 |
71
+ | 0.2976 | 2.0 | 1250 | 0.3157 | 0.9102 |
72
+ | 0.2345 | 3.0 | 1875 | 0.2768 | 0.921 |
73
 
74
 
75
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9fb84f927aa867411f6ab4d244dd5fe2b0c9c5e5863be0b485edaa2deeda067
3
  size 343290986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbbd44c7097bcff113c75cdc8a3b841b4dbd20216fe4eb4411622fa3f1d75b7
3
  size 343290986
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:001ed2a95675bb10aa5d1232127a330c0a13f8ac357b415f14b61a0e1f69cb37
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c494bbac5279c30d888a5b1227f1fcc8cc4503d0ade237df4637cd7625b3e90
3
  size 4472