Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
5
ongkn commited on
Commit
25b498c
•
1 Parent(s): 3ff32cd

End of training

Browse files
Files changed (2) hide show
  1. README.md +18 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7247191011235955
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6860
36
- - Accuracy: 0.7247
37
 
38
  ## Model description
39
 
@@ -59,24 +59,26 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: cosine
61
  - lr_scheduler_warmup_ratio: 0.05
62
- - num_epochs: 15
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.6205 | 0.5 | 100 | 0.6365 | 0.6292 |
69
- | 0.5193 | 1.0 | 200 | 0.5648 | 0.7191 |
70
- | 0.5671 | 1.5 | 300 | 0.5665 | 0.7303 |
71
- | 0.5325 | 2.0 | 400 | 0.6136 | 0.6629 |
72
- | 0.4913 | 2.5 | 500 | 0.5920 | 0.7135 |
73
- | 0.4091 | 3.0 | 600 | 0.5267 | 0.7528 |
74
- | 0.4016 | 3.5 | 700 | 0.5503 | 0.7360 |
75
- | 0.4602 | 4.0 | 800 | 0.4995 | 0.7388 |
76
- | 0.4084 | 4.5 | 900 | 0.5276 | 0.7107 |
77
- | 0.3382 | 5.0 | 1000 | 0.6308 | 0.7135 |
78
- | 0.3134 | 5.5 | 1100 | 0.6981 | 0.7079 |
79
- | 0.3497 | 6.0 | 1200 | 0.6860 | 0.7247 |
 
 
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8011049723756906
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4765
36
+ - Accuracy: 0.8011
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: cosine
61
  - lr_scheduler_warmup_ratio: 0.05
62
+ - num_epochs: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6463 | 0.49 | 100 | 0.5989 | 0.6851 |
69
+ | 0.6047 | 0.98 | 200 | 0.5202 | 0.7652 |
70
+ | 0.4682 | 1.47 | 300 | 0.5246 | 0.7541 |
71
+ | 0.5311 | 1.96 | 400 | 0.5237 | 0.7541 |
72
+ | 0.3802 | 2.45 | 500 | 0.4909 | 0.7624 |
73
+ | 0.466 | 2.94 | 600 | 0.5097 | 0.7486 |
74
+ | 0.3486 | 3.43 | 700 | 0.4766 | 0.7873 |
75
+ | 0.4283 | 3.92 | 800 | 0.5155 | 0.7403 |
76
+ | 0.3665 | 4.41 | 900 | 0.4816 | 0.7956 |
77
+ | 0.3394 | 4.9 | 1000 | 0.4591 | 0.7790 |
78
+ | 0.2687 | 5.39 | 1100 | 0.4397 | 0.8039 |
79
+ | 0.3295 | 5.88 | 1200 | 0.4463 | 0.8122 |
80
+ | 0.255 | 6.37 | 1300 | 0.4670 | 0.8094 |
81
+ | 0.2746 | 6.86 | 1400 | 0.4765 | 0.8011 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b98aacf4a231e73166ea84726a7a5b03dda2678535ac81c17a4e26a15756e901
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349987af334690cf5076b47ae32dd257675235f0431aea042800be0d36bf52c2
3
  size 343223968