Files
Qwen3-8B-Chemistry-SRPO-TR/results/training_scores.csv
ModelHub XC 2d74f845e2 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Chemistry-SRPO-TR
Source: Original Platform
2026-10-03 21:23:23 +08:00

1.3 KiB

1stepcritic_score_mean
210.453125
320.34765625
430.4453125
540.41015625
650.4375
760.4375
870.34375
980.42578125
1090.39453125
11110.5703125
12120.57421875
13130.51171875
14140.5234375
15150.56640625
16160.51953125
17170.46484375
18180.62109375
19190.62109375
20210.49609375
21220.5078125
22230.73828125
23240.6796875
24250.60546875
25260.68359375
26270.58203125
27280.60546875
28290.5625
29310.6640625
30320.60546875
31330.671875
32340.63671875
33350.59765625
34360.6484375
35370.515625
36380.66796875
37390.64453125
38410.625
39420.64453125
40430.6484375
41440.69921875
42450.6171875
43460.54296875
44470.65234375
45480.71484375
46490.7578125
47510.63671875
48520.6171875
49530.6328125
50540.61328125
51550.6953125
52560.6171875
53570.6875
54580.75390625
55590.6953125
56610.67578125
57620.6796875
58630.625
59640.765625
60650.7421875
61660.61328125
62670.66015625
63680.56640625
64690.66796875
65710.6796875
66720.73828125
67730.68359375
68740.7109375
69750.76953125
70760.609375
71770.7109375
72780.72265625
73790.6015625
74810.5859375
75820.68359375
76830.6328125
77840.71875
78850.80078125
79860.69140625
80870.69921875
81880.70703125
82890.625
83910.703125
84920.67578125
85930.8125
86940.79296875
87950.66796875
88960.72265625
89970.6796875
90980.7421875
91990.6484375