Update README.md
Browse files
README.md
CHANGED
|
@@ -73,7 +73,8 @@ Whilst it would be beneficial to add the noise on the fly during training, to en
|
|
| 73 |
|
| 74 |
### Training hyperparameters
|
| 75 |
|
| 76 |
-
|
|
|
|
| 77 |
- learning_rate: 1e-05
|
| 78 |
- train_batch_size: 8
|
| 79 |
- eval_batch_size: 8
|
|
@@ -83,6 +84,7 @@ The following hyperparameters were used during training:
|
|
| 83 |
- lr_scheduler_warmup_steps: 500
|
| 84 |
- training_steps: 10000
|
| 85 |
- mixed_precision_training: Native AMP
|
|
|
|
| 86 |
|
| 87 |
### Training results
|
| 88 |
|
|
|
|
| 73 |
|
| 74 |
### Training hyperparameters
|
| 75 |
|
| 76 |
+
<details>
|
| 77 |
+
<summary> Hyperparameters </summary>
|
| 78 |
- learning_rate: 1e-05
|
| 79 |
- train_batch_size: 8
|
| 80 |
- eval_batch_size: 8
|
|
|
|
| 84 |
- lr_scheduler_warmup_steps: 500
|
| 85 |
- training_steps: 10000
|
| 86 |
- mixed_precision_training: Native AMP
|
| 87 |
+
</details>
|
| 88 |
|
| 89 |
### Training results
|
| 90 |
|