Files
Qwen3-8B-Physics-RLSD-TR/results/training_scores.csv
ModelHub XC f104ce4822 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Physics-RLSD-TR
Source: Original Platform
2026-08-18 22:17:05 +08:00

92 lines
1.2 KiB
CSV

step,critic_score_mean
1,0.59765625
2,0.59375
3,0.546875
4,0.6640625
5,0.76171875
6,0.609375
7,0.74609375
8,0.671875
9,0.63671875
11,0.640625
12,0.5703125
13,0.55078125
14,0.6796875
15,0.69140625
16,0.76953125
17,0.68359375
18,0.421875
19,0.73046875
21,0.66015625
22,0.640625
23,0.4453125
24,0.7109375
25,0.67578125
26,0.68359375
27,0.765625
28,0.6171875
29,0.7421875
31,0.625
32,0.74609375
33,0.74609375
34,0.68359375
35,0.71875
36,0.55859375
37,0.66796875
38,0.6484375
39,0.80859375
41,0.7734375
42,0.6171875
43,0.671875
44,0.640625
45,0.69921875
46,0.734375
47,0.76171875
48,0.76171875
49,0.796875
51,0.6328125
52,0.6875
53,0.75
54,0.75
55,0.80078125
56,0.67578125
57,0.68359375
58,0.6484375
59,0.71484375
61,0.74609375
62,0.703125
63,0.6875
64,0.63671875
65,0.84375
66,0.74609375
67,0.81640625
68,0.7578125
69,0.80859375
71,0.79296875
72,0.734375
73,0.65625
74,0.81640625
75,0.8515625
76,0.70703125
77,0.703125
78,0.84765625
79,0.8203125
81,0.75
82,0.7109375
83,0.77734375
84,0.76171875
85,0.7421875
86,0.671875
87,0.75390625
88,0.65625
89,0.8671875
91,0.859375
92,0.7265625
93,0.7890625
94,0.76171875
95,0.69140625
96,0.75
97,0.84765625
98,0.74609375
99,0.8828125