Files
Qwen3-8B-Chemistry-GRPO-TR/results/training_scores.csv
ModelHub XC 73dd6958fc 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR
Source: Original Platform
2026-07-21 11:28:12 +08:00

92 lines
1.3 KiB
CSV

step,critic_score_mean
1,0.48046875
2,0.375
3,0.44921875
4,0.42578125
5,0.41015625
6,0.4140625
7,0.28125
8,0.48828125
9,0.35546875
11,0.5078125
12,0.44140625
13,0.37109375
14,0.39453125
15,0.453125
16,0.48828125
17,0.3984375
18,0.4609375
19,0.4921875
21,0.35546875
22,0.44921875
23,0.609375
24,0.49609375
25,0.5
26,0.5546875
27,0.515625
28,0.5390625
29,0.46484375
31,0.51171875
32,0.45703125
33,0.57421875
34,0.56640625
35,0.4921875
36,0.55859375
37,0.46484375
38,0.58203125
39,0.47265625
41,0.5625
42,0.55859375
43,0.5859375
44,0.60546875
45,0.58984375
46,0.46484375
47,0.5625
48,0.58203125
49,0.6484375
51,0.59375
52,0.5625
53,0.61328125
54,0.515625
55,0.61328125
56,0.5859375
57,0.60546875
58,0.63671875
59,0.50390625
61,0.6171875
62,0.63671875
63,0.46484375
64,0.73046875
65,0.66796875
66,0.60546875
67,0.6484375
68,0.41796875
69,0.5703125
71,0.59765625
72,0.69921875
73,0.578125
74,0.6796875
75,0.73828125
76,0.50390625
77,0.671875
78,0.671875
79,0.62109375
81,0.65625
82,0.58203125
83,0.55078125
84,0.69140625
85,0.71875
86,0.609375
87,0.59375
88,0.5546875
89,0.546875
91,0.6171875
92,0.62109375
93,0.8515625
94,0.72265625
95,0.7421875
96,0.640625
97,0.5859375
98,0.56640625
99,0.58984375