Commit
•
42f4d27
1
Parent(s):
8f2cdcf
Update README.md
Browse files
README.md
CHANGED
|
@@ -101,7 +101,6 @@ The model was trained **with the same prompt template of Llama-3 Instruct**.
|
|
| 101 |
|
| 102 |
The model was trained for two epochs on **8x A100 80GB GPUs using DeepSpeed ZeRO** State-3 without CPU offloading.
|
| 103 |
|
| 104 |
-
Then training lasted approximately 8 hours for a total GPU cost of 150€.
|
| 105 |
|
| 106 |
### Training hyperparameters
|
| 107 |
|
|
|
|
| 101 |
|
| 102 |
The model was trained for two epochs on **8x A100 80GB GPUs using DeepSpeed ZeRO** State-3 without CPU offloading.
|
| 103 |
|
|
|
|
| 104 |
|
| 105 |
### Training hyperparameters
|
| 106 |
|