Hugging Face's logo

rayhanozzy
/
image_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
rayhanozzy commited on
Commit
8243065
•
1 Parent(s): f5794dd

End of training

Browse files
Files changed (2) hide show
  1. README.md +26 -16
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.53125
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: 1.2556
36
- - Accuracy: 0.5312
37
 
38
  ## Model description
39
 
@@ -53,27 +53,37 @@ More information needed
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: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.2995 | 0.5125 |
68
- | No log | 2.0 | 80 | 1.3551 | 0.4813 |
69
- | No log | 3.0 | 120 | 1.2385 | 0.5375 |
70
- | No log | 4.0 | 160 | 1.2101 | 0.5437 |
71
- | No log | 5.0 | 200 | 1.3384 | 0.4688 |
72
- | No log | 6.0 | 240 | 1.3133 | 0.5188 |
73
- | No log | 7.0 | 280 | 1.2479 | 0.5312 |
74
- | No log | 8.0 | 320 | 1.2297 | 0.5563 |
75
- | No log | 9.0 | 360 | 1.1898 | 0.5687 |
76
- | No log | 10.0 | 400 | 1.3190 | 0.4813 |
 
 
 
 
 
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.58125
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: 1.5857
36
+ - Accuracy: 0.5813
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 20
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 80 | 1.4085 | 0.5062 |
68
+ | No log | 2.0 | 160 | 1.5462 | 0.5062 |
69
+ | No log | 3.0 | 240 | 1.5687 | 0.525 |
70
+ | No log | 4.0 | 320 | 1.5465 | 0.5625 |
71
+ | No log | 5.0 | 400 | 1.7599 | 0.5 |
72
+ | No log | 6.0 | 480 | 1.8047 | 0.5312 |
73
+ | 0.244 | 7.0 | 560 | 1.8441 | 0.525 |
74
+ | 0.244 | 8.0 | 640 | 1.7620 | 0.5375 |
75
+ | 0.244 | 9.0 | 720 | 1.5618 | 0.5563 |
76
+ | 0.244 | 10.0 | 800 | 1.8267 | 0.5125 |
77
+ | 0.244 | 11.0 | 880 | 1.5343 | 0.6 |
78
+ | 0.244 | 12.0 | 960 | 1.8340 | 0.5375 |
79
+ | 0.237 | 13.0 | 1040 | 1.7273 | 0.575 |
80
+ | 0.237 | 14.0 | 1120 | 1.7158 | 0.5563 |
81
+ | 0.237 | 15.0 | 1200 | 1.6075 | 0.55 |
82
+ | 0.237 | 16.0 | 1280 | 1.6131 | 0.5687 |
83
+ | 0.237 | 17.0 | 1360 | 1.8439 | 0.55 |
84
+ | 0.237 | 18.0 | 1440 | 1.9079 | 0.5188 |
85
+ | 0.1695 | 19.0 | 1520 | 1.7325 | 0.5687 |
86
+ | 0.1695 | 20.0 | 1600 | 1.5776 | 0.5938 |
87
 
88
 
89
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5428c8212e8d3db6befb22874fb2bf19499f87b1abdd1bd1f6296203b0b59297
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552f853fb83bd9daada0cd7b60958aea71aafcc106d40bdcb7250f65857b60e5
3
  size 343287149