Qwen3-4B-Biology-RLSD-TR/results/training_scores.csv

1	step	critic_score_mean
2	1	0.3125
3	2	0.4375
4	3	0.34765625
5	4	0.41796875
6	5	0.47265625
7	6	0.3125
8	7	0.22265625
9	8	0.28515625
10	9	0.3984375
11	11	0.421875
12	12	0.421875
13	13	0.34765625
14	14	0.265625
15	15	0.37890625
16	16	0.48046875
17	17	0.32421875
18	18	0.359375
19	19	0.328125
20	21	0.390625
21	22	0.46484375
22	23	0.265625
23	24	0.41015625
24	25	0.40234375
25	26	0.41015625
26	27	0.3984375
27	28	0.35546875
28	29	0.4921875
29	31	0.3828125
30	32	0.4765625
31	33	0.484375
32	34	0.37890625
33	35	0.4921875
34	36	0.33203125
35	37	0.3828125
36	38	0.50390625
37	39	0.4140625
38	41	0.54296875
39	42	0.3125
40	43	0.4921875
41	44	0.52734375
42	45	0.4140625
43	46	0.5390625
44	47	0.484375
45	48	0.46484375
46	49	0.43359375
47	51	0.37109375
48	52	0.4609375
49	53	0.4453125
50	54	0.51171875
51	55	0.5546875
52	56	0.51953125
53	57	0.60546875
54	58	0.5390625
55	59	0.53515625
56	61	0.4296875
57	62	0.51171875
58	63	0.60546875
59	64	0.4765625
60	65	0.5234375
61	66	0.53515625
62	67	0.43359375
63	68	0.52734375
64	69	0.46484375
65	71	0.48046875
66	72	0.421875
67	73	0.6171875
68	74	0.50390625
69	75	0.484375
70	76	0.46484375
71	77	0.63671875
72	78	0.58984375
73	79	0.50390625
74	81	0.59765625
75	82	0.59375
76	83	0.5859375
77	84	0.48046875
78	85	0.48828125
79	86	0.56640625
80	87	0.42578125
81	88	0.4921875
82	89	0.66796875
83	91	0.578125
84	92	0.515625
85	93	0.55078125
86	94	0.515625
87	95	0.60546875
88	96	0.53515625
89	97	0.515625
90	98	0.47265625
91	99	0.5859375