Files
Qwen3-4B-Biology-RLSD-TR/results/training_scores.csv
ModelHub XC 56d8aee6a6 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Biology-RLSD-TR
Source: Original Platform
2026-08-22 02:15:18 +08:00

92 lines
1.3 KiB
CSV

step,critic_score_mean
1,0.3125
2,0.4375
3,0.34765625
4,0.41796875
5,0.47265625
6,0.3125
7,0.22265625
8,0.28515625
9,0.3984375
11,0.421875
12,0.421875
13,0.34765625
14,0.265625
15,0.37890625
16,0.48046875
17,0.32421875
18,0.359375
19,0.328125
21,0.390625
22,0.46484375
23,0.265625
24,0.41015625
25,0.40234375
26,0.41015625
27,0.3984375
28,0.35546875
29,0.4921875
31,0.3828125
32,0.4765625
33,0.484375
34,0.37890625
35,0.4921875
36,0.33203125
37,0.3828125
38,0.50390625
39,0.4140625
41,0.54296875
42,0.3125
43,0.4921875
44,0.52734375
45,0.4140625
46,0.5390625
47,0.484375
48,0.46484375
49,0.43359375
51,0.37109375
52,0.4609375
53,0.4453125
54,0.51171875
55,0.5546875
56,0.51953125
57,0.60546875
58,0.5390625
59,0.53515625
61,0.4296875
62,0.51171875
63,0.60546875
64,0.4765625
65,0.5234375
66,0.53515625
67,0.43359375
68,0.52734375
69,0.46484375
71,0.48046875
72,0.421875
73,0.6171875
74,0.50390625
75,0.484375
76,0.46484375
77,0.63671875
78,0.58984375
79,0.50390625
81,0.59765625
82,0.59375
83,0.5859375
84,0.48046875
85,0.48828125
86,0.56640625
87,0.42578125
88,0.4921875
89,0.66796875
91,0.578125
92,0.515625
93,0.55078125
94,0.515625
95,0.60546875
96,0.53515625
97,0.515625
98,0.47265625
99,0.5859375