Update README.md
Browse files
README.md
CHANGED
|
@@ -19,11 +19,11 @@ Based on "beomi/llama-2-koen-13b"
|
|
| 19 |
|
| 20 |
## Intended uses & limitations
|
| 21 |
|
| 22 |
-
|
| 23 |
|
| 24 |
## Training and evaluation data
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
|
@@ -33,7 +33,7 @@ The following hyperparameters were used during training:
|
|
| 33 |
- learning_rate: 2e-04
|
| 34 |
- train_batch_size: 2
|
| 35 |
- eval_batch_size: 8
|
| 36 |
-
- seed:
|
| 37 |
- gradient_accumulation_steps: 1
|
| 38 |
- total_train_batch_size:
|
| 39 |
- num_epochs: 2.0
|
|
|
|
| 19 |
|
| 20 |
## Intended uses & limitations
|
| 21 |
|
| 22 |
+
T.B.D.
|
| 23 |
|
| 24 |
## Training and evaluation data
|
| 25 |
|
| 26 |
+
T.B.D.
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
|
|
|
| 33 |
- learning_rate: 2e-04
|
| 34 |
- train_batch_size: 2
|
| 35 |
- eval_batch_size: 8
|
| 36 |
+
- seed: 24
|
| 37 |
- gradient_accumulation_steps: 1
|
| 38 |
- total_train_batch_size:
|
| 39 |
- num_epochs: 2.0
|