Hugging Face's logo

Dimasnoufal
/
image_classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Dimasnoufal commited on
Commit
d00fae8
•
1 Parent(s): 7ed5130

End of training

Browse files
Files changed (2) hide show
  1. README.md +9 -16
  2. runs/Feb09_09-29-18_481290d6d8e1/events.out.tfevents.1707471104.481290d6d8e1.838.6 +3 -0
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.55
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: 1.2360
36
- - Accuracy: 0.55
37
 
38
  ## Model description
39
 
@@ -53,27 +53,20 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 45 | 1.4428 | 0.4375 |
68
- | No log | 2.0 | 90 | 1.3659 | 0.45 |
69
- | No log | 3.0 | 135 | 1.2604 | 0.55 |
70
- | No log | 4.0 | 180 | 1.2461 | 0.5125 |
71
- | No log | 5.0 | 225 | 1.0874 | 0.6625 |
72
- | No log | 6.0 | 270 | 1.1792 | 0.6 |
73
- | No log | 7.0 | 315 | 1.1221 | 0.625 |
74
- | No log | 8.0 | 360 | 1.1956 | 0.5625 |
75
- | No log | 9.0 | 405 | 1.1681 | 0.5875 |
76
- | No log | 10.0 | 450 | 1.2151 | 0.575 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6125
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: 1.1916
36
+ - Accuracy: 0.6125
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 24
57
+ - eval_batch_size: 24
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 3
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 30 | 1.2213 | 0.55 |
68
+ | No log | 2.0 | 60 | 1.3069 | 0.575 |
69
+ | No log | 3.0 | 90 | 1.1196 | 0.6125 |
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
runs/Feb09_09-29-18_481290d6d8e1/events.out.tfevents.1707471104.481290d6d8e1.838.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1567dc303b625aca128f9715dfac6c4354b388eb3082cbf57aea1820745b9395
3
+ size 405