qwen3-4b-tooluse-srpo-ema005/results/validation_mean16.csv

step,val_mean16
10,0.597426470588
20,0.567095588235
30,0.566176470588
40,0.625919117647
50,0.611213235294
60,0.606617647059
70,0.605698529412
80,0.577205882353
90,0.576286764706
100,0.572610294118
初始化项目，由ModelHub XC社区提供模型 Model: SeongryongJung/qwen3-4b-tooluse-srpo-ema005 Source: Original Platform 2026-09-20 16:14:29 +08:00			`step,val_mean16`
			`10,0.597426470588`
			`20,0.567095588235`
			`30,0.566176470588`
			`40,0.625919117647`
			`50,0.611213235294`
			`60,0.606617647059`
			`70,0.605698529412`
			`80,0.577205882353`
			`90,0.576286764706`
			`100,0.572610294118`