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

1	step	critic_score_mean
2	1	0.46484375
3	2	0.3671875
4	3	0.4140625
5	4	0.4453125
6	5	0.42578125
7	6	0.421875
8	7	0.33203125
9	8	0.46875
10	9	0.359375
11	11	0.48046875
12	12	0.46484375
13	13	0.375
14	14	0.40625
15	15	0.46875
16	16	0.47265625
17	17	0.41015625
18	18	0.49609375
19	19	0.5
20	21	0.43359375
21	22	0.4375
22	23	0.69921875
23	24	0.58984375
24	25	0.5546875
25	26	0.6328125
26	27	0.51171875
27	28	0.59765625
28	29	0.48046875
29	31	0.6015625
30	32	0.55078125
31	33	0.60546875
32	34	0.59765625
33	35	0.5078125
34	36	0.5625
35	37	0.54296875
36	38	0.6484375
37	39	0.6015625
38	41	0.62890625
39	42	0.6171875
40	43	0.61328125
41	44	0.66796875
42	45	0.5390625
43	46	0.5546875
44	47	0.64453125
45	48	0.671875
46	49	0.640625
47	51	0.5546875
48	52	0.61328125
49	53	0.62109375
50	54	0.5546875
51	55	0.640625
52	56	0.6484375
53	57	0.66796875
54	58	0.703125
55	59	0.5390625
56	61	0.66015625
57	62	0.62890625
58	63	0.53125
59	64	0.765625
60	65	0.71484375
61	66	0.6171875
62	67	0.6796875
63	68	0.46875
64	69	0.6796875
65	71	0.58984375
66	72	0.671875
67	73	0.640625
68	74	0.703125
69	75	0.71484375
70	76	0.6171875
71	77	0.7421875
72	78	0.68359375
73	79	0.609375
74	81	0.63671875
75	82	0.6015625
76	83	0.49609375
77	84	0.6875
78	85	0.71484375
79	86	0.609375
80	87	0.62109375
81	88	0.58984375
82	89	0.59765625
83	91	0.640625
84	92	0.609375
85	93	0.83203125
86	94	0.76171875
87	95	0.68359375
88	96	0.67578125
89	97	0.5625
90	98	0.609375
91	99	0.578125