gui360-fullparam-sft-step250

Full-parameter SFT on GUI-360 balanced 2K data (Qwen2.5-VL-7B-Instruct). TSR=22.2%, StepSR=69.3%. Best overall. ~epoch 3.7, LLaMA-Factory+ZeRO-3.

Base Model

  • Qwen2.5-VL-7B-Instruct

Training Data

  • GUI-360 balanced 2K episodes (17,264 steps)
  • Action types: click, type, swipe (balanced sampling)

Evaluation (GUI-360 test 1K balanced)

Metric Value
TSR (Task Success Rate) 22.2%
StepSR (Step Success Rate) 69.3%
Progress 35.3%

Full Ranking

# Method TSR Params
1 Full-param SFT step-250 22.2% 7.6B
2 V15 Cooperative RL step-25 20.8% ~142M
3 PEFT Cooperative r=128 (SVD) 18.6% ~67M
4 PEFT Standard r=128 (SVD) 18.1% ~67M
5 Base model (zero-shot) 2.4% —

Citation

Part of the Cooperative LoRA research for GUI agents.

Downloads last month
262
Safetensors
Model size
849k params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Stevenshuqing/gui360-fullparam-sft-step250

Finetuned
(1080)
this model

Dataset used to train Stevenshuqing/gui360-fullparam-sft-step250