AndrewChar
commited on
Commit
•
585307a
1
Parent(s):
0d71b13
Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ This model is a fine-tuned version of [AndrewChar/diplom-prod-epoch-4-datast-sbe
|
|
15 |
It achieves the following results on the evaluation set:
|
16 |
- Train Loss: 1.1991
|
17 |
- Validation Loss: 0.0
|
18 |
-
- Epoch:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,7 +34,7 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'
|
38 |
- training_precision: float32
|
39 |
|
40 |
### Training results
|
|
|
15 |
It achieves the following results on the evaluation set:
|
16 |
- Train Loss: 1.1991
|
17 |
- Validation Loss: 0.0
|
18 |
+
- Epoch: 5
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_re': 2e-06 'decay_steps': 2986, '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}
|
38 |
- training_precision: float32
|
39 |
|
40 |
### Training results
|