End of training
Browse files- README.md +10 -13
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,10 +15,10 @@ 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.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,21 +37,18 @@ More information needed
|
|
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':
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
-
| 2.
|
48 |
-
| 1.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.3269 | 0.3129 | 0.91 | 5 |
|
53 |
-
| 0.2794 | 0.3278 | 0.909 | 6 |
|
54 |
-
| 0.2467 | 0.3126 | 0.91 | 7 |
|
55 |
|
56 |
|
57 |
### 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: 0.3727
|
19 |
+
- Validation Loss: 0.3184
|
20 |
+
- Train Accuracy: 0.918
|
21 |
+
- Epoch: 4
|
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': 20000, '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': 0.01}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 2.7853 | 1.6126 | 0.846 | 0 |
|
48 |
+
| 1.2297 | 0.8375 | 0.877 | 1 |
|
49 |
+
| 0.7054 | 0.5339 | 0.892 | 2 |
|
50 |
+
| 0.4911 | 0.3750 | 0.919 | 3 |
|
51 |
+
| 0.3727 | 0.3184 | 0.918 | 4 |
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343773880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0303e22186b79a178018658c55976effae8cc7b46ead91ddaa3db57ce0b69f61
|
3 |
size 343773880
|