End of training
Browse files
README.md
CHANGED
|
@@ -39,8 +39,11 @@ The following hyperparameters were used during training:
|
|
| 39 |
- train_batch_size: 8
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
|
|
|
|
|
|
| 42 |
- gradient_accumulation_steps: 4
|
| 43 |
-
- total_train_batch_size:
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- training_steps: 200
|
|
|
|
| 39 |
- train_batch_size: 8
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- total_eval_batch_size: 16
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: cosine
|
| 49 |
- training_steps: 200
|