Hugging Face's logo

barten
/
vit-base-patch16-224-brand

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
barten commited on
Commit
e6b0a5e
·
1 Parent(s): 4d8c7ea

Model save

Browse files
Files changed (1) hide show
  1. README.md +19 -19
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8411297440423654
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: 0.5083
36
- - Accuracy: 0.8411
37
 
38
  ## Model description
39
 
@@ -67,26 +67,26 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.2977 | 0.99 | 106 | 1.0930 | 0.6580 |
71
- | 0.9557 | 2.0 | 213 | 0.8573 | 0.7273 |
72
- | 0.7349 | 3.0 | 320 | 0.7455 | 0.7617 |
73
- | 0.5729 | 4.0 | 427 | 0.6196 | 0.8063 |
74
- | 0.4818 | 4.99 | 533 | 0.5769 | 0.8147 |
75
- | 0.395 | 6.0 | 640 | 0.5788 | 0.8182 |
76
- | 0.3222 | 7.0 | 747 | 0.5594 | 0.8310 |
77
- | 0.3729 | 8.0 | 854 | 0.5453 | 0.8252 |
78
- | 0.265 | 8.99 | 960 | 0.5289 | 0.8389 |
79
- | 0.2409 | 10.0 | 1067 | 0.5249 | 0.8345 |
80
- | 0.1557 | 11.0 | 1174 | 0.5125 | 0.8433 |
81
- | 0.1811 | 12.0 | 1281 | 0.5123 | 0.8486 |
82
- | 0.1616 | 12.99 | 1387 | 0.5142 | 0.8491 |
83
- | 0.1481 | 14.0 | 1494 | 0.5107 | 0.8420 |
84
- | 0.1526 | 14.89 | 1590 | 0.5083 | 0.8411 |
85
 
86
 
87
  ### Framework versions
88
 
89
  - Transformers 4.35.1
90
  - Pytorch 2.1.0+cu118
91
- - Datasets 2.14.6
92
  - Tokenizers 0.14.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8398058252427184
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: 0.5298
36
+ - Accuracy: 0.8398
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.6631 | 0.99 | 106 | 1.4344 | 0.5494 |
71
+ | 1.069 | 2.0 | 213 | 0.8917 | 0.7282 |
72
+ | 0.801 | 3.0 | 320 | 0.7612 | 0.7533 |
73
+ | 0.6075 | 4.0 | 427 | 0.6522 | 0.7921 |
74
+ | 0.5046 | 4.99 | 533 | 0.6085 | 0.8005 |
75
+ | 0.4018 | 6.0 | 640 | 0.6132 | 0.8023 |
76
+ | 0.3641 | 7.0 | 747 | 0.5510 | 0.8292 |
77
+ | 0.4003 | 8.0 | 854 | 0.5304 | 0.8248 |
78
+ | 0.3142 | 8.99 | 960 | 0.5271 | 0.8350 |
79
+ | 0.2266 | 10.0 | 1067 | 0.5450 | 0.8363 |
80
+ | 0.1572 | 11.0 | 1174 | 0.5317 | 0.8323 |
81
+ | 0.1891 | 12.0 | 1281 | 0.5269 | 0.8363 |
82
+ | 0.1551 | 12.99 | 1387 | 0.5340 | 0.8376 |
83
+ | 0.1548 | 14.0 | 1494 | 0.5313 | 0.8367 |
84
+ | 0.1781 | 14.89 | 1590 | 0.5298 | 0.8398 |
85
 
86
 
87
  ### Framework versions
88
 
89
  - Transformers 4.35.1
90
  - Pytorch 2.1.0+cu118
91
+ - Datasets 2.14.7
92
  - Tokenizers 0.14.1