Update README.md
Browse files
README.md
CHANGED
|
@@ -119,7 +119,6 @@ The following hyperparameters were used during training:
|
|
| 119 |
- eval_batch_size: 1
|
| 120 |
- seed: 42
|
| 121 |
- distributed_type: multi-GPU
|
| 122 |
-
- num_devices: 8
|
| 123 |
- gradient_accumulation_steps: 8
|
| 124 |
- total_train_batch_size: 64
|
| 125 |
- total_eval_batch_size: 8
|
|
|
|
| 119 |
- eval_batch_size: 1
|
| 120 |
- seed: 42
|
| 121 |
- distributed_type: multi-GPU
|
|
|
|
| 122 |
- gradient_accumulation_steps: 8
|
| 123 |
- total_train_batch_size: 64
|
| 124 |
- total_eval_batch_size: 8
|