Commit
•
89beb04
1
Parent(s):
acec681
update model card README.md
Browse files
README.md
CHANGED
|
@@ -34,13 +34,17 @@ More information needed
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0001
|
| 37 |
-
- train_batch_size:
|
| 38 |
-
- eval_batch_size:
|
| 39 |
- seed: 2
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- lr_scheduler_warmup_ratio: 0.1
|
| 43 |
-
- training_steps:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 64
|
| 38 |
+
- eval_batch_size: 128
|
| 39 |
- seed: 2
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 2
|
| 42 |
+
- total_train_batch_size: 128
|
| 43 |
+
- total_eval_batch_size: 256
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- training_steps: 75
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|