Files
Qwen3-8B-Chemistry-GRPO-TR/results/training_scores.csv
ModelHub XC 73dd6958fc 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR
Source: Original Platform
2026-07-21 11:28:12 +08:00

1.3 KiB

1stepcritic_score_mean
210.48046875
320.375
430.44921875
540.42578125
650.41015625
760.4140625
870.28125
980.48828125
1090.35546875
11110.5078125
12120.44140625
13130.37109375
14140.39453125
15150.453125
16160.48828125
17170.3984375
18180.4609375
19190.4921875
20210.35546875
21220.44921875
22230.609375
23240.49609375
24250.5
25260.5546875
26270.515625
27280.5390625
28290.46484375
29310.51171875
30320.45703125
31330.57421875
32340.56640625
33350.4921875
34360.55859375
35370.46484375
36380.58203125
37390.47265625
38410.5625
39420.55859375
40430.5859375
41440.60546875
42450.58984375
43460.46484375
44470.5625
45480.58203125
46490.6484375
47510.59375
48520.5625
49530.61328125
50540.515625
51550.61328125
52560.5859375
53570.60546875
54580.63671875
55590.50390625
56610.6171875
57620.63671875
58630.46484375
59640.73046875
60650.66796875
61660.60546875
62670.6484375
63680.41796875
64690.5703125
65710.59765625
66720.69921875
67730.578125
68740.6796875
69750.73828125
70760.50390625
71770.671875
72780.671875
73790.62109375
74810.65625
75820.58203125
76830.55078125
77840.69140625
78850.71875
79860.609375
80870.59375
81880.5546875
82890.546875
83910.6171875
84920.62109375
85930.8515625
86940.72265625
87950.7421875
88960.640625
89970.5859375
90980.56640625
91990.58984375