Files
Qwen3-4B-Tooluse-GRPO-TR/results/training_scores.csv
ModelHub XC 9af9efe7e1 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Tooluse-GRPO-TR
Source: Original Platform
2026-08-16 11:24:56 +08:00

1.2 KiB

1stepcritic_score_mean
210.3125
320.24609375
430.34375
540.2734375
650.375
760.42578125
870.3828125
980.3046875
1090.28515625
11110.30078125
12120.359375
13130.26953125
14140.25390625
15150.5390625
16160.3125
17170.38671875
18180.3046875
19190.23828125
20210.20703125
21220.4453125
22230.20703125
23240.2890625
24250.2109375
25260.5234375
26270.375
27280.30078125
28290.171875
29310.421875
30320.28125
31330.2265625
32340.359375
33350.30078125
34360.4140625
35370.42578125
36380.3828125
37390.42578125
38410.30859375
39420.22265625
40430.3125
41440.265625
42450.25390625
43460.30859375
44470.30078125
45480.38671875
46490.2109375
47510.37109375
48520.4375
49530.36328125
50540.3359375
51550.4140625
52560.36328125
53570.4296875
54580.37109375
55590.4140625
56610.3828125
57620.33984375
58630.3671875
59640.38671875
60650.30859375
61660.421875
62670.421875
63680.46484375
64690.5390625
65710.3046875
66720.38671875
67730.33984375
68740.421875
69750.35546875
70760.25
71770.30078125
72780.375
73790.4140625
74810.40625
75820.44140625
76830.25390625
77840.46875
78850.390625
79860.40234375
80870.4375
81880.53515625
82890.30859375
83910.47265625
84920.41015625
85930.32421875
86940.3125
87950.30859375
88960.42578125
89970.33984375
90980.359375
91990.3828125