Files
Qwen3-4B-Chemistry-SDPO-TR/results/training_scores.csv
ModelHub XC f0b01151ab 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR
Source: Original Platform
2026-10-03 22:43:24 +08:00

1.3 KiB

1stepcritic_score_mean
210.59765625
320.3828125
430.4296875
540.33203125
650.4609375
760.50390625
870.4453125
980.57421875
1090.3515625
11110.45703125
12120.62109375
13130.6171875
14140.53125
15150.65625
16160.4765625
17170.41796875
18180.515625
19190.54296875
20210.5703125
21220.6015625
22230.70703125
23240.67578125
24250.5703125
25260.67578125
26270.62109375
27280.63671875
28290.44921875
29310.62109375
30320.6015625
31330.67578125
32340.6640625
33350.6015625
34360.73046875
35370.609375
36380.6484375
37390.61328125
38410.5625
39420.6875
40430.71484375
41440.6171875
42450.5234375
43460.67578125
44470.5859375
45480.66796875
46490.73828125
47510.625
48520.5078125
49530.6640625
50540.51171875
51550.7421875
52560.58984375
53570.671875
54580.76171875
55590.63671875
56610.69140625
57620.7109375
58630.58984375
59640.84375
60650.7578125
61660.59375
62670.59765625
63680.609375
64690.60546875
65710.59375
66720.70703125
67730.61328125
68740.73046875
69750.71484375
70760.5625
71770.63671875
72780.69140625
73790.63671875
74810.609375
75820.67578125
76830.640625
77840.7578125
78850.7578125
79860.5546875
80870.734375
81880.6640625
82890.640625
83910.671875
84920.7265625
85930.7890625
86940.828125
87950.7578125
88960.671875
89970.6640625
90980.70703125
91990.68359375