https://github.com/glavin001/llm-trainer
Training/Fine-Tuning Large Language Models
https://github.com/glavin001/llm-trainer
Last synced: about 1 month ago
JSON representation
Training/Fine-Tuning Large Language Models
- Host: GitHub
- URL: https://github.com/glavin001/llm-trainer
- Owner: Glavin001
- License: mit
- Created: 2023-05-28T02:30:13.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2023-05-29T07:56:56.000Z (almost 2 years ago)
- Last Synced: 2025-02-05T15:54:06.872Z (3 months ago)
- Language: Jupyter Notebook
- Size: 69.3 KB
- Stars: 2
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LLM Trainer
> Training/Fine-Tuning Large Language Models
Login to Docker:
```bash
sudo docker login
```
Pull existing Docker image to warm build cache:
```bash
sudo docker pull glavin001/llm-trainer:may-28-433
```
Build & start container with Jupyter labs/notebook:
```bash
sudo docker compose up --build
```
If you see error:
> tornado.web.HTTPError: HTTP 403: Forbidden
Then stop the docker container and retry.
Login to Weights and Biases:
```bash
wandb login -u USERNAME
```
```bash
./scripts/train.sh
```