Files
Qwen3-8B-Chemistry-SDPO-TR/results/training_scores.csv
ModelHub XC 6a1fa758ea 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Chemistry-SDPO-TR
Source: Original Platform
2026-10-12 20:44:06 +08:00

1.2 KiB

1stepcritic_score_mean
210.5234375
320.40234375
430.3828125
540.44921875
650.4609375
760.43359375
870.31640625
980.51953125
1090.359375
11110.58984375
12120.58203125
13130.578125
14140.59765625
15150.56640625
16160.55859375
17170.48828125
18180.625
19190.65625
20210.515625
21220.5
22230.75
23240.7109375
24250.671875
25260.71484375
26270.65234375
27280.703125
28290.578125
29310.68359375
30320.67578125
31330.66796875
32340.7109375
33350.59765625
34360.734375
35370.57421875
36380.6796875
37390.625
38410.6484375
39420.7265625
40430.703125
41440.6640625
42450.62109375
43460.53125
44470.71484375
45480.6875
46490.78515625
47510.61328125
48520.64453125
49530.7109375
50540.609375
51550.71875
52560.640625
53570.69140625
54580.828125
55590.66015625
56610.68359375
57620.671875
58630.57421875
59640.8359375
60650.8125
61660.6640625
62670.71875
63680.515625
64690.70703125
65710.73046875
66720.796875
67730.7109375
68740.734375
69750.78125
70760.65625
71770.7421875
72780.76953125
73790.67578125
74810.671875
75820.6875
76830.57421875
77840.73828125
78850.76171875
79860.66015625
80870.78125
81880.75
82890.671875
83910.7265625
84920.62890625
85930.89453125
86940.81640625
87950.71875
88960.734375
89970.6953125
90980.69921875
91990.625