Files
Qwen3-4B-Chemical-RLSD-TR/results/training_scores.csv
ModelHub XC 110a0a7a0c 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemical-RLSD-TR
Source: Original Platform
2026-08-14 23:14:45 +08:00

92 lines
1.2 KiB
CSV

step,critic_score_mean
1,0.5546875
2,0.3828125
3,0.453125
4,0.33984375
5,0.484375
6,0.44140625
7,0.40625
8,0.52734375
9,0.32421875
11,0.421875
12,0.4609375
13,0.47265625
14,0.453125
15,0.4921875
16,0.42578125
17,0.41015625
18,0.421875
19,0.515625
21,0.375
22,0.375
23,0.59375
24,0.5078125
25,0.48828125
26,0.62890625
27,0.5
28,0.5859375
29,0.34375
31,0.625
32,0.5625
33,0.65234375
34,0.515625
35,0.5078125
36,0.64453125
37,0.515625
38,0.59765625
39,0.59765625
41,0.59375
42,0.5859375
43,0.62890625
44,0.6171875
45,0.53515625
46,0.54296875
47,0.609375
48,0.5859375
49,0.65234375
51,0.5390625
52,0.59375
53,0.57421875
54,0.50390625
55,0.609375
56,0.64453125
57,0.578125
58,0.64453125
59,0.58203125
61,0.65234375
62,0.64453125
63,0.48828125
64,0.70703125
65,0.74609375
66,0.546875
67,0.66796875
68,0.4765625
69,0.56640625
71,0.5859375
72,0.71484375
73,0.546875
74,0.62109375
75,0.73046875
76,0.5625
77,0.7265625
78,0.65234375
79,0.59765625
81,0.640625
82,0.625
83,0.5625
84,0.68359375
85,0.69921875
86,0.5625
87,0.53125
88,0.57421875
89,0.625
91,0.60546875
92,0.625
93,0.87890625
94,0.73046875
95,0.6640625
96,0.6015625
97,0.52734375
98,0.58203125
99,0.640625