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
1af051b
·
verified ·
1 Parent(s): 6784cc6

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.809322033898305
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: 0.5064
36
- - Accuracy: 0.8093
37
 
38
  ## Model description
39
 
@@ -59,7 +59,7 @@ The following hyperparameters were used during training:
59
  - gradient_accumulation_steps: 8
60
  - total_train_batch_size: 256
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
- - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.05
64
  - num_epochs: 25
65
  - mixed_precision_training: Native AMP
@@ -68,13 +68,18 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 0.4908 | 3.01 | 50 | 0.5141 | 0.7797 |
72
- | 0.3766 | 6.02 | 100 | 0.4485 | 0.7839 |
73
- | 0.3121 | 9.02 | 150 | 0.4550 | 0.7903 |
74
- | 0.2569 | 12.03 | 200 | 0.3977 | 0.8305 |
75
- | 0.215 | 15.04 | 250 | 0.4732 | 0.7987 |
76
- | 0.186 | 18.05 | 300 | 0.4804 | 0.8072 |
77
- | 0.1568 | 21.05 | 350 | 0.5064 | 0.8093 |
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8114406779661016
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: 0.4385
36
+ - Accuracy: 0.8114
37
 
38
  ## Model description
39
 
 
59
  - gradient_accumulation_steps: 8
60
  - total_train_batch_size: 256
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: cosine
63
  - lr_scheduler_warmup_ratio: 0.05
64
  - num_epochs: 25
65
  - mixed_precision_training: Native AMP
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.65 | 1.5 | 25 | 0.5581 | 0.7394 |
72
+ | 0.4953 | 3.01 | 50 | 0.4969 | 0.7542 |
73
+ | 0.4541 | 4.51 | 75 | 0.4627 | 0.7775 |
74
+ | 0.38 | 6.02 | 100 | 0.4566 | 0.7839 |
75
+ | 0.3357 | 7.52 | 125 | 0.4352 | 0.8072 |
76
+ | 0.307 | 9.02 | 150 | 0.4656 | 0.7881 |
77
+ | 0.2701 | 10.53 | 175 | 0.4294 | 0.8093 |
78
+ | 0.244 | 12.03 | 200 | 0.4797 | 0.8114 |
79
+ | 0.2294 | 13.53 | 225 | 0.4235 | 0.8263 |
80
+ | 0.2017 | 15.04 | 250 | 0.4744 | 0.8157 |
81
+ | 0.199 | 16.54 | 275 | 0.4450 | 0.8136 |
82
+ | 0.1793 | 18.05 | 300 | 0.4385 | 0.8114 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e83dcf82e3783b9130ab6117920f1496d8011215782446d85dbeab51720a7ba
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d674d65adc829a7f6323b8600e56454040fa91203e8b90570a53293f95e26c1e
3
  size 343223968