Model save
Browse files
README.md
CHANGED
|
@@ -32,13 +32,14 @@ More information needed
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate:
|
| 36 |
- train_batch_size: 32
|
| 37 |
- eval_batch_size: 32
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: cosine_with_restarts
|
| 41 |
-
-
|
|
|
|
| 42 |
|
| 43 |
### Framework versions
|
| 44 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 1e-05
|
| 36 |
- train_batch_size: 32
|
| 37 |
- eval_batch_size: 32
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: cosine_with_restarts
|
| 41 |
+
- lr_scheduler_warmup_steps: 100
|
| 42 |
+
- num_epochs: 20
|
| 43 |
|
| 44 |
### Framework versions
|
| 45 |
|