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

step,val_mean16
10,0.59453125
20,0.61328125
30,0.63125
40,0.62421875
50,0.6453125
60,0.6375
70,0.63828125
80,0.6390625
90,0.6625
100,0.6828125
初始化项目，由ModelHub XC社区提供模型 Model: SeongryongJung/Qwen3-4B-Physics-GRPO-TR Source: Original Platform 2026-08-05 02:49:18 +08:00			`step,val_mean16`
			`10,0.59453125`
			`20,0.61328125`
			`30,0.63125`
			`40,0.62421875`
			`50,0.6453125`
			`60,0.6375`
			`70,0.63828125`
			`80,0.6390625`
			`90,0.6625`
			`100,0.6828125`