Hugging Face's logo

aditnnda
/
felidae_klasifikasi

Image Classification
Transformers
TensorFlow
vit
generated_from_keras_callback
Inference Endpoints
Model card Files Community
aditnnda commited on
Commit
d9da3a7
•
1 Parent(s): 1ce753a

End of training

Browse files
Files changed (2) hide show
  1. README.md +26 -16
  2. tf_model.h5 +2 -2
README.md CHANGED
@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.9213
19
- - Train Accuracy: 0.7869
20
- - Validation Loss: 0.8231
21
- - Validation Accuracy: 0.7869
22
- - Epoch: 9
23
 
24
  ## Model description
25
 
@@ -38,23 +38,33 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1820, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
42
  - training_precision: float32
43
 
44
  ### Training results
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
- | 1.6070 | 0.3770 | 1.5670 | 0.3770 | 0 |
49
- | 1.5299 | 0.6557 | 1.4816 | 0.6557 | 1 |
50
- | 1.4347 | 0.6066 | 1.3838 | 0.6066 | 2 |
51
- | 1.3535 | 0.6885 | 1.2822 | 0.6885 | 3 |
52
- | 1.2562 | 0.6885 | 1.1766 | 0.6885 | 4 |
53
- | 1.1829 | 0.7705 | 1.0732 | 0.7705 | 5 |
54
- | 1.1037 | 0.8033 | 0.9889 | 0.8033 | 6 |
55
- | 1.0444 | 0.8525 | 0.9204 | 0.8525 | 7 |
56
- | 0.9640 | 0.8197 | 0.8722 | 0.8197 | 8 |
57
- | 0.9213 | 0.7869 | 0.8231 | 0.7869 | 9 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.5782
19
+ - Train Accuracy: 0.8361
20
+ - Validation Loss: 0.5283
21
+ - Validation Accuracy: 0.8361
22
+ - Epoch: 19
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 3640, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
42
  - training_precision: float32
43
 
44
  ### Training results
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
+ | 1.5945 | 0.5574 | 1.5482 | 0.5574 | 0 |
49
+ | 1.5213 | 0.7541 | 1.4625 | 0.7541 | 1 |
50
+ | 1.4429 | 0.7049 | 1.3574 | 0.7049 | 2 |
51
+ | 1.3399 | 0.7869 | 1.2390 | 0.7869 | 3 |
52
+ | 1.2264 | 0.6721 | 1.1328 | 0.6721 | 4 |
53
+ | 1.1660 | 0.7869 | 1.0287 | 0.7869 | 5 |
54
+ | 1.0825 | 0.7377 | 0.9690 | 0.7377 | 6 |
55
+ | 1.0005 | 0.8197 | 0.8654 | 0.8197 | 7 |
56
+ | 0.9121 | 0.7869 | 0.8303 | 0.7869 | 8 |
57
+ | 0.8530 | 0.8525 | 0.7590 | 0.8525 | 9 |
58
+ | 0.8602 | 0.8361 | 0.7169 | 0.8361 | 10 |
59
+ | 0.8420 | 0.8197 | 0.6993 | 0.8197 | 11 |
60
+ | 0.7772 | 0.8689 | 0.6347 | 0.8689 | 12 |
61
+ | 0.7447 | 0.8689 | 0.6023 | 0.8689 | 13 |
62
+ | 0.7253 | 0.8197 | 0.6458 | 0.8197 | 14 |
63
+ | 0.6994 | 0.8361 | 0.6045 | 0.8361 | 15 |
64
+ | 0.6761 | 0.8361 | 0.6030 | 0.8361 | 16 |
65
+ | 0.5814 | 0.8197 | 0.5523 | 0.8197 | 17 |
66
+ | 0.5939 | 0.8689 | 0.5456 | 0.8689 | 18 |
67
+ | 0.5782 | 0.8361 | 0.5283 | 0.8361 | 19 |
68
 
69
 
70
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc07e52accc52e6c0cebd830c7d0297e4a0b6052ff281d47528000971fed514a
3
- size 343478968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca016f193afa5c1ab756bf808d0f3f8303a4c8ba57f30e5689b2c3b69305981d
3
+ size 343495352