Commit
•
ca5e34b
1
Parent(s):
8910a9d
End of training
Browse files- README.md +25 -10
- 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:
|
19 |
-
- Validation Loss:
|
20 |
-
- Train Accuracy: 0.
|
21 |
-
- Epoch:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,18 +37,33 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', '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 |
-
| 2.
|
49 |
-
| 2.
|
50 |
-
| 1.
|
51 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### 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: 0.7312
|
19 |
+
- Validation Loss: 0.9257
|
20 |
+
- Train Accuracy: 0.8
|
21 |
+
- Epoch: 19
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1600, '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}
|
41 |
- training_precision: float32
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
46 |
|:----------:|:---------------:|:--------------:|:-----:|
|
47 |
+
| 2.2668 | 2.2081 | 0.4 | 0 |
|
48 |
+
| 2.1502 | 2.1140 | 0.6 | 1 |
|
49 |
+
| 2.0506 | 2.0350 | 0.65 | 2 |
|
50 |
+
| 1.9473 | 1.9239 | 0.7 | 3 |
|
51 |
+
| 1.8164 | 1.8355 | 0.7 | 4 |
|
52 |
+
| 1.7091 | 1.7534 | 0.75 | 5 |
|
53 |
+
| 1.6152 | 1.6683 | 0.8 | 6 |
|
54 |
+
| 1.5122 | 1.5825 | 0.8 | 7 |
|
55 |
+
| 1.4108 | 1.4897 | 0.8 | 8 |
|
56 |
+
| 1.3225 | 1.4149 | 0.8 | 9 |
|
57 |
+
| 1.2426 | 1.3135 | 0.8 | 10 |
|
58 |
+
| 1.1740 | 1.2704 | 0.8 | 11 |
|
59 |
+
| 1.0894 | 1.2213 | 0.85 | 12 |
|
60 |
+
| 1.0230 | 1.1424 | 0.8 | 13 |
|
61 |
+
| 0.9646 | 1.1171 | 0.85 | 14 |
|
62 |
+
| 0.9109 | 1.0744 | 0.8 | 15 |
|
63 |
+
| 0.8547 | 1.0376 | 0.85 | 16 |
|
64 |
+
| 0.8082 | 0.9892 | 0.8 | 17 |
|
65 |
+
| 0.7632 | 0.9604 | 0.85 | 18 |
|
66 |
+
| 0.7312 | 0.9257 | 0.8 | 19 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343510712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2566a58081f770e7bc72f7bc19c4159537538d0774567932205d82c9eb67af3
|
3 |
size 343510712
|