Hugging Face's logo

ahmadalfian
/
image_classification

TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files Metrics Community
ahmadalfian commited on
Commit
fbf0614
·
verified ·
1 Parent(s): 79bbcc7

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.58125
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: 1.1334
36
- - Accuracy: 0.5813
37
 
38
  ## Model description
39
 
@@ -56,27 +56,27 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 8
57
  - eval_batch_size: 32
58
  - seed: 42
59
- - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_ratio: 0.2
64
  - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0287 | 1.0 | 40 | 1.9886 | 0.3312 |
71
- | 1.6572 | 2.0 | 80 | 1.6017 | 0.4 |
72
- | 1.4274 | 3.0 | 120 | 1.3753 | 0.5 |
73
- | 1.2165 | 4.0 | 160 | 1.2923 | 0.5125 |
74
- | 1.0676 | 5.0 | 200 | 1.2017 | 0.5437 |
75
- | 0.9438 | 6.0 | 240 | 1.1987 | 0.525 |
76
- | 0.7568 | 7.0 | 280 | 1.1113 | 0.5625 |
77
- | 0.6683 | 8.0 | 320 | 1.1406 | 0.5625 |
78
- | 0.5162 | 9.0 | 360 | 1.1863 | 0.5625 |
79
- | 0.4258 | 10.0 | 400 | 1.0780 | 0.65 |
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6375
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: 1.1228
36
+ - Accuracy: 0.6375
37
 
38
  ## Model description
39
 
 
56
  - train_batch_size: 8
57
  - eval_batch_size: 32
58
  - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.2101 | 1.0 | 20 | 1.3528 | 0.5062 |
71
+ | 1.0583 | 2.0 | 40 | 1.3027 | 0.5312 |
72
+ | 0.9272 | 3.0 | 60 | 1.2388 | 0.5625 |
73
+ | 0.7279 | 4.0 | 80 | 1.2505 | 0.5625 |
74
+ | 0.6103 | 5.0 | 100 | 1.2658 | 0.4938 |
75
+ | 0.5925 | 6.0 | 120 | 1.2039 | 0.5375 |
76
+ | 0.4836 | 7.0 | 140 | 1.3076 | 0.5062 |
77
+ | 0.4743 | 8.0 | 160 | 1.2393 | 0.55 |
78
+ | 0.3937 | 9.0 | 180 | 1.1658 | 0.5813 |
79
+ | 0.3831 | 10.0 | 200 | 1.2273 | 0.55 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca96fb83283c51bd345925d453a89752b9c21654aed06f6200065e87d4cc936d
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7e60407244f7a8cb04eb34f20cf4a68a59b4f73fac6ea88fbd1df452b0d665
3
  size 343242432