Update README.md
#1
by
Jyotiyadav
- opened
README.md
CHANGED
|
@@ -20,3 +20,20 @@ base_model: unsloth/llama-3-8b-bnb-4bit
|
|
| 20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
# Results
|
| 27 |
+
|
| 28 |
+
| Step | Training Loss |
|
| 29 |
+
|------|---------------|
|
| 30 |
+
| 5 | 1.748100 |
|
| 31 |
+
| 10 | 1.584900 |
|
| 32 |
+
| 15 | 1.406200 |
|
| 33 |
+
| 20 | 1.274800 |
|
| 34 |
+
| 25 | 0.983400 |
|
| 35 |
+
| 30 | 0.939900 |
|
| 36 |
+
| 35 | 1.156100 |
|
| 37 |
+
| 40 | 0.883000 |
|
| 38 |
+
| 45 | 0.813900 |
|
| 39 |
+
| 50 | 0.721000 |
|