Commit
·
7ab6a2e
1
Parent(s):
adac510
End of training
Browse files
README.md
CHANGED
|
@@ -32,14 +32,14 @@ More information needed
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate: 0.
|
| 36 |
-
- train_batch_size:
|
| 37 |
-
- eval_batch_size:
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
-
- lr_scheduler_warmup_steps:
|
| 42 |
-
- training_steps:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0005
|
| 36 |
+
- train_batch_size: 4
|
| 37 |
+
- eval_batch_size: 4
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_steps: 70
|
| 42 |
+
- training_steps: 8500
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|