Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
-
- arxiv:2410.12391
|
| 5 |
datasets:
|
| 6 |
- nilq/baby-python
|
| 7 |
metrics:
|
|
@@ -26,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
|
| 27 |
# baby-python-mistral-1L-tiny-base
|
| 28 |
|
| 29 |
-
This model is
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
- Loss: 3.1027
|
| 32 |
- Accuracy: 0.4190
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
| 4 |
datasets:
|
| 5 |
- nilq/baby-python
|
| 6 |
metrics:
|
|
|
|
| 25 |
|
| 26 |
# baby-python-mistral-1L-tiny-base
|
| 27 |
|
| 28 |
+
This model is trained on the nilq/baby-python dataset. It is the base model in the paper [Tracking Universal Features Through Fine-Tuning and Model Merging](https://arxiv.org/abs/2410.12391).
|
| 29 |
It achieves the following results on the evaluation set:
|
| 30 |
- Loss: 3.1027
|
| 31 |
- Accuracy: 0.4190
|