Files
Qwen3-8B-Biology-GRPO-TR/results/training_scores.csv
ModelHub XC 67b8171dec 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Biology-GRPO-TR
Source: Original Platform
2026-08-11 09:55:18 +08:00

1.3 KiB

1stepcritic_score_mean
210.35546875
320.41015625
430.46875
540.37109375
650.484375
760.39453125
870.3359375
980.28515625
1090.3359375
11110.375
12120.43359375
13130.3125
14140.35546875
15150.3671875
16160.453125
17170.23046875
18180.34765625
19190.453125
20210.4765625
21220.51171875
22230.3515625
23240.37890625
24250.40625
25260.37109375
26270.38671875
27280.3671875
28290.45703125
29310.35546875
30320.47265625
31330.4765625
32340.37890625
33350.50390625
34360.3828125
35370.4296875
36380.4375
37390.5546875
38410.50390625
39420.40625
40430.53515625
41440.47265625
42450.4375
43460.41796875
44470.390625
45480.5390625
46490.42578125
47510.4609375
48520.54296875
49530.4140625
50540.44140625
51550.546875
52560.4765625
53570.5546875
54580.46484375
55590.46875
56610.38671875
57620.5078125
58630.59765625
59640.5859375
60650.5546875
61660.46484375
62670.48046875
63680.62890625
64690.40625
65710.5234375
66720.4765625
67730.5703125
68740.44921875
69750.51953125
70760.3671875
71770.609375
72780.66015625
73790.4765625
74810.5625
75820.62109375
76830.54296875
77840.51171875
78850.45703125
79860.51953125
80870.484375
81880.453125
82890.6328125
83910.4765625
84920.6015625
85930.55859375
86940.44921875
87950.61328125
88960.59375
89970.62890625
90980.46484375
91990.49609375