namhokaist/appgen-qwen3-thinktag-lr5e-7-ep1-continue-sft-norm1000-nav-only

appgen-qwen3-thinktag-lr5e-7-ep1-continue-sft-norm1000-nav-only

Continue-SFT checkpoint of luca0621/appgen-qwen3-thinktag-lr5e-7-ep1 trained on navigation-only GUI data in the mobile_use tool-call format.

• —Base model: luca0621/appgen-qwen3-thinktag-lr5e-7-ep1
• —Output format: mobile_use tool call with normalized 0-1000 coordinates
• —Dataset: mobile_use_norm1000, navigation-only split
• —Training: 1 epoch, learning rate 5e-7, full fine-tuning, max length 4096
• —Checkpoint: checkpoint-2406

Real-World Eval

Evaluation was run with prompt style gelab, coordinate space 0-1000 point-in-bbox, and fixed image pixels 2629536.

• —Average accuracy: 82.50%
• —Weighted average accuracy: 79.36%
• —Total correct: 5468 / 6890
• —Bad format: 0