pretrain core 4
Browse files
scripts/pretrain_core_model_4.yaml
CHANGED
|
@@ -60,7 +60,7 @@ train:
|
|
| 60 |
# Number of samples between optimizer steps across data-parallel ranks (type: int, default: 512)
|
| 61 |
# global_batch_size: 512
|
| 62 |
# global_batch_size: 256
|
| 63 |
-
global_batch_size:
|
| 64 |
|
| 65 |
# Number of samples per data-parallel rank (type: int, default: 4)
|
| 66 |
micro_batch_size: 1
|
|
|
|
| 60 |
# Number of samples between optimizer steps across data-parallel ranks (type: int, default: 512)
|
| 61 |
# global_batch_size: 512
|
| 62 |
# global_batch_size: 256
|
| 63 |
+
global_batch_size: 64
|
| 64 |
|
| 65 |
# Number of samples per data-parallel rank (type: int, default: 4)
|
| 66 |
micro_batch_size: 1
|