Files
Qwen3-4B-Chemistry-RLRT-TR/results/training_scores.csv
ModelHub XC 22e0cd8b2b 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemistry-RLRT-TR
Source: Original Platform
2026-10-03 20:29:22 +08:00

1.2 KiB

1stepcritic_score_mean
210.58203125
320.36328125
430.4765625
540.32421875
650.4765625
760.46484375
870.37109375
980.53125
1090.3671875
11110.44921875
12120.5390625
13130.421875
14140.41796875
15150.484375
16160.45703125
17170.35546875
18180.40234375
19190.5390625
20210.375
21220.32421875
22230.55078125
23240.56640625
24250.43359375
25260.5546875
26270.44921875
27280.53515625
28290.36328125
29310.5625
30320.5078125
31330.47265625
32340.48828125
33350.4453125
34360.51953125
35370.41015625
36380.4765625
37390.48046875
38410.35546875
39420.40625
40430.484375
41440.61328125
42450.578125
43460.40234375
44470.484375
45480.41015625
46490.5546875
47510.640625
48520.4375
49530.59375
50540.34765625
51550.55859375
52560.45703125
53570.46875
54580.50390625
55590.4375
56610.51953125
57620.5078125
58630.53515625
59640.6328125
60650.5859375
61660.5390625
62670.5703125
63680.3359375
64690.5859375
65710.54296875
66720.56640625
67730.5703125
68740.52734375
69750.6875
70760.55859375
71770.59765625
72780.578125
73790.47265625
74810.453125
75820.61328125
76830.48828125
77840.58203125
78850.6484375
79860.4375
80870.3984375
81880.53515625
82890.5625
83910.45703125
84920.546875
85930.6875
86940.64453125
87950.59375
88960.5078125
89970.48046875
90980.4609375
91990.4921875