metadata
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
Uploaded model
- Developed by: sxandie
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Results
| Step | Training Loss |
|---|---|
| 5 | 1.748100 |
| 10 | 1.584900 |
| 15 | 1.406200 |
| 20 | 1.274800 |
| 25 | 0.983400 |
| 30 | 0.939900 |
| 35 | 1.156100 |
| 40 | 0.883000 |
| 45 | 0.813900 |
| 50 | 0.721000 |