zeeshaan-ai/solo-tune-test66

test_finetuned66

Model Details

Base Model	Qwen/Qwen3-0.6B
Method	LoRA (PEFT)
Parameters	0.6B

Training Hyperparameters

Epochs	2
Max Steps	100
Batch Size	2
Gradient Accumulation	4
Learning Rate	0.0002
LoRA r	4
LoRA Alpha	4
Max Sequence Length	2048
Training Duration	4m 31s

Dataset

GetSoloTech/Code-Reasoning

---

_{Fine-tuned using Solo}