Files
Qwen3-4B-Biology-GRPO-TR/results/training_scores.csv
ModelHub XC 7d17112db8 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Biology-GRPO-TR
Source: Original Platform
2026-10-03 20:15:22 +08:00

92 lines
1.2 KiB
CSV

step,critic_score_mean
1,0.3515625
2,0.36328125
3,0.37890625
4,0.4140625
5,0.4609375
6,0.32421875
7,0.29296875
8,0.26953125
9,0.3984375
11,0.44140625
12,0.45703125
13,0.35546875
14,0.26953125
15,0.34765625
16,0.546875
17,0.28515625
18,0.3359375
19,0.40625
21,0.40625
22,0.49609375
23,0.25390625
24,0.36328125
25,0.3828125
26,0.41015625
27,0.296875
28,0.34765625
29,0.296875
31,0.375
32,0.5078125
33,0.453125
34,0.3828125
35,0.35546875
36,0.34375
37,0.359375
38,0.43359375
39,0.3828125
41,0.48828125
42,0.328125
43,0.44140625
44,0.4375
45,0.31640625
46,0.46484375
47,0.39453125
48,0.35546875
49,0.34765625
51,0.4140625
52,0.42578125
53,0.51953125
54,0.48046875
55,0.51171875
56,0.42578125
57,0.44140625
58,0.59375
59,0.5390625
61,0.28125
62,0.46484375
63,0.39453125
64,0.4921875
65,0.4375
66,0.4296875
67,0.52734375
68,0.47265625
69,0.42578125
71,0.44921875
72,0.5
73,0.66015625
74,0.42578125
75,0.3828125
76,0.43359375
77,0.6171875
78,0.43359375
79,0.41015625
81,0.5390625
82,0.59375
83,0.5234375
84,0.4296875
85,0.5
86,0.63671875
87,0.5234375
88,0.375
89,0.58984375
91,0.53515625
92,0.65234375
93,0.484375
94,0.48046875
95,0.53125
96,0.61328125
97,0.56640625
98,0.4140625
99,0.578125