ash001/ray-tune-qwen-0.5B

Qwen2-0.5B Fine-tuned with Ray Tune Hyperparameter Optimization

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct, optimized using Ray Tune with ASHA scheduler for automated hyperparameter search across 6 trials to find the optimal configuration.

This model was fine-tuned using the IMDB dataset on 2 × T4 16GB GPUs with automated hyperparameter optimization across learning rate, batch size, weight decay, epochs, and warmup steps.

For detailed implementation, Ray Tune configurations, and hyperparameter search setup, please check out the project repository.