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

1	step	val_mean16
2	10	0.32625
3	20	0.3575
4	30	0.3825
5	40	0.35375
6	50	0.41875
7	60	0.3825
8	70	0.395
9	80	0.41625
10	90	0.4675
11	100	0.42625