Model save
Browse files
README.md
CHANGED
|
@@ -32,15 +32,15 @@ More information needed
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0002
|
| 35 |
-
- train_batch_size:
|
| 36 |
- eval_batch_size: 8
|
| 37 |
- seed: 42
|
| 38 |
- gradient_accumulation_steps: 16
|
| 39 |
-
- total_train_batch_size:
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
-
- lr_scheduler_type:
|
| 42 |
- lr_scheduler_warmup_ratio: 0.03
|
| 43 |
-
-
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0002
|
| 35 |
+
- train_batch_size: 10
|
| 36 |
- eval_batch_size: 8
|
| 37 |
- seed: 42
|
| 38 |
- gradient_accumulation_steps: 16
|
| 39 |
+
- total_train_batch_size: 160
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: cosine
|
| 42 |
- lr_scheduler_warmup_ratio: 0.03
|
| 43 |
+
- training_steps: 100
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|