Hugging Face's logo

grahmatagung
/
image_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
grahmatagung commited on
Commit
b4b1301
•
1 Parent(s): edc3784

End of training

Browse files
Files changed (3) hide show
  1. README.md +29 -9
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5125
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: 1.4759
36
- - Accuracy: 0.5125
37
 
38
  ## Model description
39
 
@@ -58,17 +58,37 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.8393 | 0.3063 |
68
- | No log | 2.0 | 80 | 1.6213 | 0.4313 |
69
- | No log | 3.0 | 120 | 1.5417 | 0.4125 |
70
- | No log | 4.0 | 160 | 1.5002 | 0.4875 |
71
- | No log | 5.0 | 200 | 1.4791 | 0.4813 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.625
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: 1.1877
36
+ - Accuracy: 0.625
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 25
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 1.8317 | 0.2938 |
68
+ | No log | 2.0 | 80 | 1.5647 | 0.4437 |
69
+ | No log | 3.0 | 120 | 1.4497 | 0.4938 |
70
+ | No log | 4.0 | 160 | 1.3529 | 0.5188 |
71
+ | No log | 5.0 | 200 | 1.2883 | 0.5125 |
72
+ | No log | 6.0 | 240 | 1.2861 | 0.5125 |
73
+ | No log | 7.0 | 280 | 1.2655 | 0.55 |
74
+ | No log | 8.0 | 320 | 1.2890 | 0.5125 |
75
+ | No log | 9.0 | 360 | 1.1955 | 0.575 |
76
+ | No log | 10.0 | 400 | 1.2180 | 0.5687 |
77
+ | No log | 11.0 | 440 | 1.2835 | 0.55 |
78
+ | No log | 12.0 | 480 | 1.2838 | 0.5188 |
79
+ | 1.0368 | 13.0 | 520 | 1.2168 | 0.5875 |
80
+ | 1.0368 | 14.0 | 560 | 1.1713 | 0.6312 |
81
+ | 1.0368 | 15.0 | 600 | 1.2222 | 0.5875 |
82
+ | 1.0368 | 16.0 | 640 | 1.3160 | 0.5563 |
83
+ | 1.0368 | 17.0 | 680 | 1.2512 | 0.6125 |
84
+ | 1.0368 | 18.0 | 720 | 1.3575 | 0.5563 |
85
+ | 1.0368 | 19.0 | 760 | 1.3514 | 0.5375 |
86
+ | 1.0368 | 20.0 | 800 | 1.3472 | 0.5625 |
87
+ | 1.0368 | 21.0 | 840 | 1.3449 | 0.5375 |
88
+ | 1.0368 | 22.0 | 880 | 1.3783 | 0.5375 |
89
+ | 1.0368 | 23.0 | 920 | 1.3240 | 0.575 |
90
+ | 1.0368 | 24.0 | 960 | 1.3391 | 0.5687 |
91
+ | 0.2885 | 25.0 | 1000 | 1.3723 | 0.55 |
92
 
93
 
94
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12bcfdc1de2f7b1dfbffdeeba900254d0b642622185de1235026d3ac783076f
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbfd33f5d70d0a9389bfad27b82a0b19f84741e740c278014c2bf24419a55e86
3
  size 343287149
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9b2d5ba11aade51dcf3f2578c190367d7ff1d1a8dc9e14671e5562a658e31ac
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a037501e05d75455f6209cde757028f7a0f29708e5768d0a58fbe3b217c9fc88
3
  size 4091