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

1	step	val_mean16
2	10	0.305
3	20	0.29875
4	30	0.41125
5	40	0.39125
6	50	0.37625
7	60	0.475
8	70	0.46
9	80	0.4875
10	90	0.50375
11	100	0.49875