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
1c351b1
•
1 Parent(s): 13856f4

End of training

Browse files
Files changed (1) hide show
  1. README.md +23 -23
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6
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: 1.3404
36
- - Accuracy: 0.6
37
 
38
  ## Model description
39
 
@@ -64,26 +64,26 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 80 | 1.7388 | 0.4188 |
68
- | No log | 2.0 | 160 | 1.5325 | 0.4313 |
69
- | No log | 3.0 | 240 | 1.3682 | 0.4938 |
70
- | No log | 4.0 | 320 | 1.3711 | 0.4813 |
71
- | No log | 5.0 | 400 | 1.4485 | 0.425 |
72
- | No log | 6.0 | 480 | 1.2649 | 0.5 |
73
- | 1.2824 | 7.0 | 560 | 1.3907 | 0.4813 |
74
- | 1.2824 | 8.0 | 640 | 1.4983 | 0.4437 |
75
- | 1.2824 | 9.0 | 720 | 1.2882 | 0.5625 |
76
- | 1.2824 | 10.0 | 800 | 1.3375 | 0.5375 |
77
- | 1.2824 | 11.0 | 880 | 1.2640 | 0.5437 |
78
- | 1.2824 | 12.0 | 960 | 1.3920 | 0.5188 |
79
- | 0.5037 | 13.0 | 1040 | 1.3629 | 0.575 |
80
- | 0.5037 | 14.0 | 1120 | 1.4067 | 0.5625 |
81
- | 0.5037 | 15.0 | 1200 | 1.3189 | 0.5813 |
82
- | 0.5037 | 16.0 | 1280 | 1.3454 | 0.575 |
83
- | 0.5037 | 17.0 | 1360 | 1.5200 | 0.5312 |
84
- | 0.5037 | 18.0 | 1440 | 1.3378 | 0.6062 |
85
- | 0.2616 | 19.0 | 1520 | 1.4539 | 0.5563 |
86
- | 0.2616 | 20.0 | 1600 | 1.4415 | 0.5437 |
87
 
88
 
89
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5625
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: 1.3383
36
+ - Accuracy: 0.5625
37
 
38
  ## Model description
39
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 80 | 1.6519 | 0.3312 |
68
+ | No log | 2.0 | 160 | 1.4509 | 0.4125 |
69
+ | No log | 3.0 | 240 | 1.3641 | 0.5062 |
70
+ | No log | 4.0 | 320 | 1.2676 | 0.5875 |
71
+ | No log | 5.0 | 400 | 1.2718 | 0.5188 |
72
+ | No log | 6.0 | 480 | 1.2250 | 0.5125 |
73
+ | 1.2828 | 7.0 | 560 | 1.1933 | 0.55 |
74
+ | 1.2828 | 8.0 | 640 | 1.1538 | 0.575 |
75
+ | 1.2828 | 9.0 | 720 | 1.2479 | 0.55 |
76
+ | 1.2828 | 10.0 | 800 | 1.2487 | 0.575 |
77
+ | 1.2828 | 11.0 | 880 | 1.2418 | 0.5938 |
78
+ | 1.2828 | 12.0 | 960 | 1.1514 | 0.6062 |
79
+ | 0.5147 | 13.0 | 1040 | 1.2563 | 0.5563 |
80
+ | 0.5147 | 14.0 | 1120 | 1.2933 | 0.5813 |
81
+ | 0.5147 | 15.0 | 1200 | 1.2857 | 0.5813 |
82
+ | 0.5147 | 16.0 | 1280 | 1.3044 | 0.575 |
83
+ | 0.5147 | 17.0 | 1360 | 1.4134 | 0.5687 |
84
+ | 0.5147 | 18.0 | 1440 | 1.3277 | 0.5875 |
85
+ | 0.2675 | 19.0 | 1520 | 1.2963 | 0.575 |
86
+ | 0.2675 | 20.0 | 1600 | 1.2049 | 0.6125 |
87
 
88
 
89
  ### Framework versions