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

92 lines
1.2 KiB
CSV

step,critic_score_mean
1,0.25390625
2,0.18359375
3,0.19921875
4,0.28515625
5,0.2890625
6,0.31640625
7,0.47265625
8,0.3359375
9,0.296875
11,0.3984375
12,0.26953125
13,0.39453125
14,0.30859375
15,0.30078125
16,0.21875
17,0.40234375
18,0.38671875
19,0.44921875
21,0.3125
22,0.359375
23,0.49609375
24,0.26953125
25,0.34375
26,0.4140625
27,0.2421875
28,0.5
29,0.1796875
31,0.3828125
32,0.44140625
33,0.234375
34,0.27734375
35,0.33203125
36,0.43359375
37,0.3046875
38,0.19140625
39,0.44921875
41,0.24609375
42,0.33984375
43,0.296875
44,0.296875
45,0.421875
46,0.25
47,0.37109375
48,0.265625
49,0.3515625
51,0.30078125
52,0.25
53,0.4140625
54,0.3984375
55,0.26953125
56,0.30859375
57,0.30859375
58,0.4140625
59,0.37890625
61,0.2890625
62,0.4921875
63,0.4296875
64,0.2890625
65,0.4140625
66,0.28125
67,0.29296875
68,0.28125
69,0.29296875
71,0.484375
72,0.34375
73,0.28515625
74,0.3046875
75,0.44921875
76,0.29296875
77,0.375
78,0.25
79,0.421875
81,0.4453125
82,0.38671875
83,0.48046875
84,0.30078125
85,0.38671875
86,0.4453125
87,0.33984375
88,0.31640625
89,0.43359375
91,0.40625
92,0.3828125
93,0.3125
94,0.3671875
95,0.4140625
96,0.35546875
97,0.35546875
98,0.35546875
99,0.44140625