Hugging Face's logo

METEoRS
/
my_awesome_food_model

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
METEoRS commited on
Commit
ea08269
•
1 Parent(s): 02d7264

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -11
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  name: food101
17
  type: food101
18
  config: default
19
- split: train[:1000]
20
  args: default
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.985
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-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.1792
35
- - Accuracy: 0.985
36
 
37
  ## Model description
38
 
@@ -60,20 +60,27 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 3
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.0534 | 1.0 | 50 | 1.8898 | 0.945 |
70
- | 1.2673 | 2.0 | 100 | 1.3131 | 0.98 |
71
- | 1.143 | 3.0 | 150 | 1.1792 | 0.985 |
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.29.2
77
- - Pytorch 2.0.0+cu118
78
  - Datasets 2.12.0
79
  - Tokenizers 0.13.3
 
16
  name: food101
17
  type: food101
18
  config: default
19
+ split: train[:20200]
20
  args: default
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8853960396039604
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 food101 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.4703
35
+ - Accuracy: 0.8854
36
 
37
  ## Model description
38
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 10
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
69
+ | 1.4019 | 1.0 | 1010 | 1.3796 | 0.8156 |
70
+ | 0.6238 | 2.0 | 2020 | 0.6604 | 0.8448 |
71
+ | 0.3691 | 3.0 | 3030 | 0.5661 | 0.8522 |
72
+ | 0.3947 | 4.0 | 4040 | 0.5226 | 0.8614 |
73
+ | 0.3511 | 5.0 | 5050 | 0.5125 | 0.8644 |
74
+ | 0.2504 | 6.0 | 6060 | 0.5180 | 0.8656 |
75
+ | 0.1285 | 7.0 | 7070 | 0.5312 | 0.8668 |
76
+ | 0.2301 | 8.0 | 8080 | 0.4779 | 0.875 |
77
+ | 0.0844 | 9.0 | 9090 | 0.4823 | 0.8839 |
78
+ | 0.1189 | 10.0 | 10100 | 0.4703 | 0.8854 |
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.29.2
84
+ - Pytorch 2.0.1+cu118
85
  - Datasets 2.12.0
86
  - Tokenizers 0.13.3