End of training
Browse files- README.md +14 -17
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -14,10 +14,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
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.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
-
|
19 |
-
-
|
20 |
-
-
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,23 +37,19 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps':
|
40 |
- training_precision: float32
|
41 |
|
42 |
### Training results
|
43 |
|
44 |
-
| Train Loss | Validation Loss |
|
45 |
-
|
46 |
-
|
|
47 |
-
| 0.
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.5580 | 0.4655 | 0.7917 | 6 |
|
53 |
-
| 0.5796 | 0.4462 | 0.8333 | 7 |
|
54 |
-
| 0.4934 | 0.4899 | 0.8542 | 8 |
|
55 |
-
| 0.5020 | 0.4878 | 0.8125 | 9 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
14 |
|
15 |
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.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.8652
|
18 |
+
- Train Accuracy: 0.75
|
19 |
+
- Validation Loss: 0.7771
|
20 |
+
- Validation Accuracy: 0.75
|
21 |
+
- Epoch: 5
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1600, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.05}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
+
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|
46 |
+
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
|
47 |
+
| 0.9228 | 0.7 | 0.9388 | 0.7000 | 0 |
|
48 |
+
| 0.9711 | 0.775 | 0.8639 | 0.7750 | 1 |
|
49 |
+
| 0.8841 | 0.825 | 0.8585 | 0.8250 | 2 |
|
50 |
+
| 0.8757 | 0.65 | 0.8448 | 0.6500 | 3 |
|
51 |
+
| 0.8802 | 0.75 | 0.7883 | 0.75 | 4 |
|
52 |
+
| 0.8652 | 0.75 | 0.7771 | 0.75 | 5 |
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343472824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bebfdb94957f3cadc2a037c1abd5920238a490d5e2f6a6ed94bf61b70547e35
|
3 |
size 343472824
|