Hugging Face's logo

WillyArdiyanto
/
image_classification

Image Classification
Transformers
PyTorch
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
WillyArdiyanto commited on
Commit
52007a5
•
1 Parent(s): c83204e

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -8
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.44375
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: 1.6176
36
- - Accuracy: 0.4437
37
 
38
  ## Model description
39
 
@@ -52,21 +52,28 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 3
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.8684 | 0.3875 |
68
- | No log | 2.0 | 80 | 1.6556 | 0.4437 |
69
- | No log | 3.0 | 120 | 1.6144 | 0.45 |
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.3375
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: 1.7506
36
+ - Accuracy: 0.3375
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 2.0529 | 0.2313 |
68
+ | No log | 2.0 | 80 | 2.0309 | 0.2062 |
69
+ | No log | 3.0 | 120 | 1.9924 | 0.2437 |
70
+ | No log | 4.0 | 160 | 1.9320 | 0.275 |
71
+ | No log | 5.0 | 200 | 1.8763 | 0.2938 |
72
+ | No log | 6.0 | 240 | 1.8214 | 0.3 |
73
+ | No log | 7.0 | 280 | 1.7866 | 0.3063 |
74
+ | No log | 8.0 | 320 | 1.7660 | 0.3 |
75
+ | No log | 9.0 | 360 | 1.7510 | 0.3312 |
76
+ | No log | 10.0 | 400 | 1.7487 | 0.3438 |
77
 
78
 
79
  ### Framework versions