Update README.md
Browse files
README.md
CHANGED
|
@@ -61,8 +61,6 @@ The following hyperparameters were used during training:
|
|
| 61 |
- train_batch_size: 16
|
| 62 |
- eval_batch_size: 16
|
| 63 |
- seed: 42
|
| 64 |
-
- gradient_accumulation_steps: 2
|
| 65 |
-
- total_train_batch_size: 32
|
| 66 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 67 |
- lr_scheduler_type: linear
|
| 68 |
- lr_scheduler_warmup_steps: 500
|
|
|
|
| 61 |
- train_batch_size: 16
|
| 62 |
- eval_batch_size: 16
|
| 63 |
- seed: 42
|
|
|
|
|
|
|
| 64 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 65 |
- lr_scheduler_type: linear
|
| 66 |
- lr_scheduler_warmup_steps: 500
|