Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: peft
|
| 3 |
tags:
|
| 4 |
- trl
|
| 5 |
- sft
|
|
@@ -19,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [kam414/pre-train-mistral-v2-full](https://huggingface.co/kam414/pre-train-mistral-v2-full) on the generator dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 1.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -55,8 +54,6 @@ The following hyperparameters were used during training:
|
|
| 55 |
| 1.3178 | 1.0 | 20 | 1.2463 |
|
| 56 |
| 1.071 | 1.5 | 30 | 1.2405 |
|
| 57 |
| 1.0554 | 2.0 | 40 | 1.2212 |
|
| 58 |
-
| 0.8008 | 2.5 | 50 | 1.3185 |
|
| 59 |
-
| 0.765 | 3.0 | 60 | 1.3072 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- trl
|
| 4 |
- sft
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [kam414/pre-train-mistral-v2-full](https://huggingface.co/kam414/pre-train-mistral-v2-full) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2212
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 54 |
| 1.3178 | 1.0 | 20 | 1.2463 |
|
| 55 |
| 1.071 | 1.5 | 30 | 1.2405 |
|
| 56 |
| 1.0554 | 2.0 | 40 | 1.2212 |
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|