Qwen3-8B-Biology-GRPO-TR/results/validation_mean16.csv

step,val_mean16
10,0.305
20,0.29875
30,0.41125
40,0.39125
50,0.37625
60,0.475
70,0.46
80,0.4875
90,0.50375
100,0.49875
初始化项目，由ModelHub XC社区提供模型 Model: SeongryongJung/Qwen3-8B-Biology-GRPO-TR Source: Original Platform 2026-08-11 09:55:18 +08:00			`step,val_mean16`
			`10,0.305`
			`20,0.29875`
			`30,0.41125`
			`40,0.39125`
			`50,0.37625`
			`60,0.475`
			`70,0.46`
			`80,0.4875`
			`90,0.50375`
			`100,0.49875`