Commit ·
849f94c
1
Parent(s): ce1c33c
update model card README.md
Browse files
README.md
CHANGED
|
@@ -31,15 +31,15 @@ More information needed
|
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
| 33 |
- learning_rate: 5e-05
|
| 34 |
-
- train_batch_size:
|
| 35 |
-
- eval_batch_size:
|
| 36 |
- seed: 42
|
| 37 |
-
- gradient_accumulation_steps:
|
| 38 |
-
- total_train_batch_size:
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 15
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
| 33 |
- learning_rate: 5e-05
|
| 34 |
+
- train_batch_size: 42
|
| 35 |
+
- eval_batch_size: 42
|
| 36 |
- seed: 42
|
| 37 |
+
- gradient_accumulation_steps: 20
|
| 38 |
+
- total_train_batch_size: 840
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 15
|
| 42 |
+
- num_epochs: 300
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|