Hugging Face's logo

Mrohit01
/
cards-vit-base-patch16-224-finetuned-v1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Mrohit01 commited on
Commit
23794c7
·
verified ·
1 Parent(s): 22c4f83

Model save

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.3192410001773364
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: 1.6835
36
- - Accuracy: 0.3192
37
 
38
  ## Model description
39
 
@@ -67,21 +67,21 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | 1.7866 | 0.9993 | 378 | 1.7677 | 0.2746 |
71
- | 1.7457 | 1.9987 | 756 | 1.7163 | 0.2990 |
72
- | 1.7123 | 2.9980 | 1134 | 1.6862 | 0.3007 |
73
- | 1.6607 | 4.0 | 1513 | 1.6823 | 0.3081 |
74
- | 1.6188 | 4.9993 | 1891 | 1.6907 | 0.3108 |
75
- | 1.6009 | 5.9987 | 2269 | 1.6773 | 0.3150 |
76
- | 1.5485 | 6.9980 | 2647 | 1.6720 | 0.3198 |
77
- | 1.5133 | 8.0 | 3026 | 1.6811 | 0.3199 |
78
- | 1.5001 | 8.9993 | 3404 | 1.6821 | 0.3209 |
79
- | 1.4303 | 9.9934 | 3780 | 1.6835 | 0.3192 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.40.1
85
- - Pytorch 2.3.0+cu121
86
  - Datasets 2.19.1
87
  - Tokenizers 0.19.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.31704202872849796
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: 1.9972
36
+ - Accuracy: 0.3170
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
+ | 1.7068 | 0.9993 | 378 | 1.9533 | 0.2753 |
71
+ | 1.6691 | 1.9987 | 756 | 1.9642 | 0.2864 |
72
+ | 1.6278 | 2.9980 | 1134 | 1.9935 | 0.3018 |
73
+ | 1.5837 | 4.0 | 1513 | 2.0155 | 0.3077 |
74
+ | 1.5263 | 4.9993 | 1891 | 2.0283 | 0.3063 |
75
+ | 1.4969 | 5.9987 | 2269 | 2.0026 | 0.3081 |
76
+ | 1.5088 | 6.9980 | 2647 | 2.0275 | 0.3098 |
77
+ | 1.4623 | 8.0 | 3026 | 2.0096 | 0.3137 |
78
+ | 1.4305 | 8.9993 | 3404 | 2.0239 | 0.3154 |
79
+ | 1.3895 | 9.9934 | 3780 | 1.9972 | 0.3170 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.40.1
85
+ - Pytorch 2.0.1+cu117
86
  - Datasets 2.19.1
87
  - Tokenizers 0.19.1