Files
Qwen3-8B-Biology-GRPO-TR/results/training_scores.csv
ModelHub XC 67b8171dec 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Biology-GRPO-TR
Source: Original Platform
2026-08-11 09:55:18 +08:00

92 lines
1.3 KiB
CSV

step,critic_score_mean
1,0.35546875
2,0.41015625
3,0.46875
4,0.37109375
5,0.484375
6,0.39453125
7,0.3359375
8,0.28515625
9,0.3359375
11,0.375
12,0.43359375
13,0.3125
14,0.35546875
15,0.3671875
16,0.453125
17,0.23046875
18,0.34765625
19,0.453125
21,0.4765625
22,0.51171875
23,0.3515625
24,0.37890625
25,0.40625
26,0.37109375
27,0.38671875
28,0.3671875
29,0.45703125
31,0.35546875
32,0.47265625
33,0.4765625
34,0.37890625
35,0.50390625
36,0.3828125
37,0.4296875
38,0.4375
39,0.5546875
41,0.50390625
42,0.40625
43,0.53515625
44,0.47265625
45,0.4375
46,0.41796875
47,0.390625
48,0.5390625
49,0.42578125
51,0.4609375
52,0.54296875
53,0.4140625
54,0.44140625
55,0.546875
56,0.4765625
57,0.5546875
58,0.46484375
59,0.46875
61,0.38671875
62,0.5078125
63,0.59765625
64,0.5859375
65,0.5546875
66,0.46484375
67,0.48046875
68,0.62890625
69,0.40625
71,0.5234375
72,0.4765625
73,0.5703125
74,0.44921875
75,0.51953125
76,0.3671875
77,0.609375
78,0.66015625
79,0.4765625
81,0.5625
82,0.62109375
83,0.54296875
84,0.51171875
85,0.45703125
86,0.51953125
87,0.484375
88,0.453125
89,0.6328125
91,0.4765625
92,0.6015625
93,0.55859375
94,0.44921875
95,0.61328125
96,0.59375
97,0.62890625
98,0.46484375
99,0.49609375