Qwen3-8B-Biology-RLSD-TR/results/training_scores.csv

1	step	critic_score_mean
2	1	0.33984375
3	2	0.3828125
4	3	0.44921875
5	4	0.37890625
6	5	0.44921875
7	6	0.34375
8	7	0.2890625
9	8	0.2421875
10	9	0.34765625
11	11	0.42578125
12	12	0.421875
13	13	0.3203125
14	14	0.29296875
15	15	0.3671875
16	16	0.40234375
17	17	0.30078125
18	18	0.4296875
19	19	0.3828125
20	21	0.4140625
21	22	0.4296875
22	23	0.33984375
23	24	0.453125
24	25	0.4296875
25	26	0.38671875
26	27	0.359375
27	28	0.375
28	29	0.4375
29	31	0.31640625
30	32	0.5
31	33	0.41015625
32	34	0.390625
33	35	0.4765625
34	36	0.390625
35	37	0.4140625
36	38	0.44140625
37	39	0.4765625
38	41	0.45703125
39	42	0.3515625
40	43	0.56640625
41	44	0.4921875
42	45	0.40234375
43	46	0.4140625
44	47	0.40625
45	48	0.48046875
46	49	0.43359375
47	51	0.4375
48	52	0.53515625
49	53	0.48828125
50	54	0.5
51	55	0.609375
52	56	0.53515625
53	57	0.53515625
54	58	0.4921875
55	59	0.4921875
56	61	0.46875
57	62	0.5078125
58	63	0.5546875
59	64	0.65625
60	65	0.57421875
61	66	0.45703125
62	67	0.515625
63	68	0.5859375
64	69	0.49609375
65	71	0.50390625
66	72	0.5546875
67	73	0.59765625
68	74	0.45703125
69	75	0.55859375
70	76	0.4765625
71	77	0.6640625
72	78	0.640625
73	79	0.47265625
74	81	0.59375
75	82	0.58203125
76	83	0.5390625
77	84	0.50390625
78	85	0.5
79	86	0.56640625
80	87	0.578125
81	88	0.44140625
82	89	0.6328125
83	91	0.4921875
84	92	0.6328125
85	93	0.6015625
86	94	0.609375
87	95	0.6640625
88	96	0.6484375
89	97	0.65625
90	98	0.4609375
91	99	0.54296875