Hugging Face's logo

Augusto777
/
vit-base-patch16-224-RU5-10

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
87b97af
·
verified ·
1 Parent(s): f10fd06

Model save

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. runs/May24_07-57-29_DESKTOP-SKBE9FB/events.out.tfevents.1716559050.DESKTOP-SKBE9FB.10960.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5833333333333334
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.2348
36
- - Accuracy: 0.5833
37
 
38
  ## Model description
39
 
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 2 | 1.3715 | 0.4833 |
71
- | No log | 2.0 | 4 | 1.3415 | 0.4667 |
72
- | No log | 3.0 | 6 | 1.3148 | 0.4667 |
73
- | No log | 4.0 | 8 | 1.2919 | 0.4833 |
74
- | 1.3369 | 5.0 | 10 | 1.2726 | 0.4833 |
75
- | 1.3369 | 6.0 | 12 | 1.2569 | 0.5 |
76
- | 1.3369 | 7.0 | 14 | 1.2442 | 0.55 |
77
- | 1.3369 | 8.0 | 16 | 1.2348 | 0.5833 |
78
- | 1.3369 | 9.0 | 18 | 1.2287 | 0.5833 |
79
- | 1.2441 | 10.0 | 20 | 1.2261 | 0.5667 |
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7166666666666667
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8134
36
+ - Accuracy: 0.7167
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.92 | 9 | 1.2939 | 0.4667 |
71
+ | 1.3501 | 1.95 | 19 | 1.1706 | 0.5833 |
72
+ | 1.2272 | 2.97 | 29 | 1.0594 | 0.6333 |
73
+ | 1.0941 | 4.0 | 39 | 0.9773 | 0.6 |
74
+ | 0.979 | 4.92 | 48 | 0.9142 | 0.6833 |
75
+ | 0.8694 | 5.95 | 58 | 0.8569 | 0.7 |
76
+ | 0.7662 | 6.97 | 68 | 0.8364 | 0.6833 |
77
+ | 0.7002 | 8.0 | 78 | 0.8071 | 0.7 |
78
+ | 0.6443 | 8.92 | 87 | 0.8095 | 0.7333 |
79
+ | 0.629 | 9.23 | 90 | 0.8134 | 0.7167 |
80
 
81
 
82
  ### Framework versions
runs/May24_07-57-29_DESKTOP-SKBE9FB/events.out.tfevents.1716559050.DESKTOP-SKBE9FB.10960.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6683ae154cf5d2ad98df9885bfeed539ad16daf84f05c512ec5ad9f27fe17f87
3
- size 8574
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d962a8ff6b54064ba974dab113f07543e8220653e0a2765db88fbd0b863cefeb
3
+ size 9393