Qwen3-4B-Material-GRPO-TR/results/validation_mean16.csv

step,val_mean16
10,0.6688829787234043
20,0.6954787234042553
30,0.7167553191489362
40,0.7393617021276596
50,0.754654255319149
60,0.7659574468085106
70,0.75
80,0.7506648936170213
90,0.7566489361702128
100,0.7626329787234043
初始化项目，由ModelHub XC社区提供模型 Model: SeongryongJung/Qwen3-4B-Material-GRPO-TR Source: Original Platform 2026-08-04 08:21:18 +08:00			`step,val_mean16`
			`10,0.6688829787234043`
			`20,0.6954787234042553`
			`30,0.7167553191489362`
			`40,0.7393617021276596`
			`50,0.754654255319149`
			`60,0.7659574468085106`
			`70,0.75`
			`80,0.7506648936170213`
			`90,0.7566489361702128`
			`100,0.7626329787234043`