Files
Qwen3-4B-Chemistry-SRPO-TR/results/training_scores.csv
ModelHub XC a8fcfca3cd 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemistry-SRPO-TR
Source: Original Platform
2026-09-21 17:54:26 +08:00

1.3 KiB

1stepcritic_score_mean
210.59375
320.37890625
430.41796875
540.3671875
650.50390625
760.421875
870.36328125
980.51953125
1090.33203125
11110.50390625
12120.55078125
13130.54296875
14140.57421875
15150.55859375
16160.49609375
17170.44140625
18180.53515625
19190.62890625
20210.45703125
21220.45703125
22230.7421875
23240.703125
24250.6796875
25260.64453125
26270.53515625
27280.6953125
28290.55078125
29310.62109375
30320.6328125
31330.625
32340.63671875
33350.58984375
34360.66015625
35370.5390625
36380.6484375
37390.64453125
38410.609375
39420.6484375
40430.68359375
41440.625
42450.625
43460.60546875
44470.671875
45480.671875
46490.765625
47510.59765625
48520.52734375
49530.6484375
50540.6015625
51550.62890625
52560.5546875
53570.671875
54580.71875
55590.57421875
56610.60546875
57620.60546875
58630.53125
59640.76171875
60650.7265625
61660.5703125
62670.62890625
63680.546875
64690.58203125
65710.6640625
66720.75
67730.61328125
68740.71875
69750.80078125
70760.66015625
71770.703125
72780.73828125
73790.66015625
74810.57421875
75820.63671875
76830.6171875
77840.78515625
78850.81640625
79860.6796875
80870.65234375
81880.62109375
82890.671875
83910.77734375
84920.6875
85930.77734375
86940.8203125
87950.5859375
88960.7109375
89970.60546875
90980.75
91990.62109375