Files
Qwen3-4B-Tooluse-RLSD-TR/results/training_scores.csv
ModelHub XC a52fcb1e1d 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Tooluse-RLSD-TR
Source: Original Platform
2026-08-20 04:49:19 +08:00

1.2 KiB

1stepcritic_score_mean
210.25390625
320.18359375
430.19921875
540.28515625
650.2890625
760.31640625
870.47265625
980.3359375
1090.296875
11110.3984375
12120.26953125
13130.39453125
14140.30859375
15150.30078125
16160.21875
17170.40234375
18180.38671875
19190.44921875
20210.3125
21220.359375
22230.49609375
23240.26953125
24250.34375
25260.4140625
26270.2421875
27280.5
28290.1796875
29310.3828125
30320.44140625
31330.234375
32340.27734375
33350.33203125
34360.43359375
35370.3046875
36380.19140625
37390.44921875
38410.24609375
39420.33984375
40430.296875
41440.296875
42450.421875
43460.25
44470.37109375
45480.265625
46490.3515625
47510.30078125
48520.25
49530.4140625
50540.3984375
51550.26953125
52560.30859375
53570.30859375
54580.4140625
55590.37890625
56610.2890625
57620.4921875
58630.4296875
59640.2890625
60650.4140625
61660.28125
62670.29296875
63680.28125
64690.29296875
65710.484375
66720.34375
67730.28515625
68740.3046875
69750.44921875
70760.29296875
71770.375
72780.25
73790.421875
74810.4453125
75820.38671875
76830.48046875
77840.30078125
78850.38671875
79860.4453125
80870.33984375
81880.31640625
82890.43359375
83910.40625
84920.3828125
85930.3125
86940.3671875
87950.4140625
88960.35546875
89970.35546875
90980.35546875
91990.44140625