Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,14 @@ It achieves the following results on the evaluation set:
|
|
| 19 |
|
| 20 |
Too many warmup steps as a result loss did not go down much. This model is suboptimal.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
More information needed
|
|
|
|
| 19 |
|
| 20 |
Too many warmup steps as a result loss did not go down much. This model is suboptimal.
|
| 21 |
|
| 22 |
+
## Training Script
|
| 23 |
+
|
| 24 |
+
https://github.com/habanoz/llm-sft/
|
| 25 |
+
|
| 26 |
+
## Training Setup
|
| 27 |
+
|
| 28 |
+
Trained on Sagemaker ml.g5.xlarge for 1 hour(s), 43 minute(s), and 30 second(s).
|
| 29 |
+
|
| 30 |
## Model description
|
| 31 |
|
| 32 |
More information needed
|