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

1	step	critic_score_mean
2	1	0.5546875
3	2	0.3828125
4	3	0.453125
5	4	0.33984375
6	5	0.484375
7	6	0.44140625
8	7	0.40625
9	8	0.52734375
10	9	0.32421875
11	11	0.421875
12	12	0.4609375
13	13	0.47265625
14	14	0.453125
15	15	0.4921875
16	16	0.42578125
17	17	0.41015625
18	18	0.421875
19	19	0.515625
20	21	0.375
21	22	0.375
22	23	0.59375
23	24	0.5078125
24	25	0.48828125
25	26	0.62890625
26	27	0.5
27	28	0.5859375
28	29	0.34375
29	31	0.625
30	32	0.5625
31	33	0.65234375
32	34	0.515625
33	35	0.5078125
34	36	0.64453125
35	37	0.515625
36	38	0.59765625
37	39	0.59765625
38	41	0.59375
39	42	0.5859375
40	43	0.62890625
41	44	0.6171875
42	45	0.53515625
43	46	0.54296875
44	47	0.609375
45	48	0.5859375
46	49	0.65234375
47	51	0.5390625
48	52	0.59375
49	53	0.57421875
50	54	0.50390625
51	55	0.609375
52	56	0.64453125
53	57	0.578125
54	58	0.64453125
55	59	0.58203125
56	61	0.65234375
57	62	0.64453125
58	63	0.48828125
59	64	0.70703125
60	65	0.74609375
61	66	0.546875
62	67	0.66796875
63	68	0.4765625
64	69	0.56640625
65	71	0.5859375
66	72	0.71484375
67	73	0.546875
68	74	0.62109375
69	75	0.73046875
70	76	0.5625
71	77	0.7265625
72	78	0.65234375
73	79	0.59765625
74	81	0.640625
75	82	0.625
76	83	0.5625
77	84	0.68359375
78	85	0.69921875
79	86	0.5625
80	87	0.53125
81	88	0.57421875
82	89	0.625
83	91	0.60546875
84	92	0.625
85	93	0.87890625
86	94	0.73046875
87	95	0.6640625
88	96	0.6015625
89	97	0.52734375
90	98	0.58203125
91	99	0.640625