Files
qwen3-4b-tooluse-srpo-ema005/results/training_scores.csv
ModelHub XC 9aabae373d 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/qwen3-4b-tooluse-srpo-ema005
Source: Original Platform
2026-09-20 16:14:29 +08:00

92 lines
1.3 KiB
CSV

step,critic_score_mean
1,0.259765625
2,0.328125
3,0.421875
4,0.326171875
5,0.31640625
6,0.37109375
7,0.318359375
8,0.4453125
9,0.4140625
11,0.353515625
12,0.357421875
13,0.330078125
14,0.3828125
15,0.296875
16,0.279296875
17,0.384765625
18,0.4140625
19,0.2578125
21,0.353515625
22,0.314453125
23,0.380859375
24,0.359375
25,0.265625
26,0.41015625
27,0.400390625
28,0.34765625
29,0.369140625
31,0.400390625
32,0.302734375
33,0.203125
34,0.318359375
35,0.384765625
36,0.359375
37,0.271484375
38,0.337890625
39,0.38671875
41,0.40625
42,0.23828125
43,0.31640625
44,0.263671875
45,0.390625
46,0.392578125
47,0.435546875
48,0.326171875
49,0.30078125
51,0.5859375
52,0.337890625
53,0.384765625
54,0.30859375
55,0.474609375
56,0.318359375
57,0.361328125
58,0.33984375
59,0.27734375
61,0.384765625
62,0.33203125
63,0.373046875
64,0.416015625
65,0.474609375
66,0.47265625
67,0.373046875
68,0.228515625
69,0.501953125
71,0.328125
72,0.3828125
73,0.30859375
74,0.310546875
75,0.353515625
76,0.416015625
77,0.470703125
78,0.3984375
79,0.3828125
81,0.31640625
82,0.341796875
83,0.419921875
84,0.369140625
85,0.3046875
86,0.3046875
87,0.375
88,0.455078125
89,0.318359375
91,0.361328125
92,0.330078125
93,0.4375
94,0.34765625
95,0.314453125
96,0.328125
97,0.298828125
98,0.421875
99,0.431640625