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

step,val_mean16
10,0.4398809523809524
20,0.5059523809523809
30,0.5526785714285715
40,0.5904761904761905
50,0.6318452380952381
60,0.6482142857142857
70,0.655952380952381
80,0.6657738095238095
90,0.6788690476190476
100,0.6880952380952381
初始化项目，由ModelHub XC社区提供模型 Model: SeongryongJung/Qwen3-4B-Chemical-GRPO-TR Source: Original Platform 2026-08-09 20:57:18 +08:00			`step,val_mean16`
			`10,0.4398809523809524`
			`20,0.5059523809523809`
			`30,0.5526785714285715`
			`40,0.5904761904761905`
			`50,0.6318452380952381`
			`60,0.6482142857142857`
			`70,0.655952380952381`
			`80,0.6657738095238095`
			`90,0.6788690476190476`
			`100,0.6880952380952381`