Files
Qwen3-8B-Chemistry-RLSD-TR/results/training_scores.csv
ModelHub XC d3719d800b 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR
Source: Original Platform
2026-07-21 17:57:12 +08:00

92 lines
1.2 KiB
CSV

step,critic_score_mean
1,0.46484375
2,0.3671875
3,0.4140625
4,0.4453125
5,0.42578125
6,0.421875
7,0.33203125
8,0.46875
9,0.359375
11,0.48046875
12,0.46484375
13,0.375
14,0.40625
15,0.46875
16,0.47265625
17,0.41015625
18,0.49609375
19,0.5
21,0.43359375
22,0.4375
23,0.69921875
24,0.58984375
25,0.5546875
26,0.6328125
27,0.51171875
28,0.59765625
29,0.48046875
31,0.6015625
32,0.55078125
33,0.60546875
34,0.59765625
35,0.5078125
36,0.5625
37,0.54296875
38,0.6484375
39,0.6015625
41,0.62890625
42,0.6171875
43,0.61328125
44,0.66796875
45,0.5390625
46,0.5546875
47,0.64453125
48,0.671875
49,0.640625
51,0.5546875
52,0.61328125
53,0.62109375
54,0.5546875
55,0.640625
56,0.6484375
57,0.66796875
58,0.703125
59,0.5390625
61,0.66015625
62,0.62890625
63,0.53125
64,0.765625
65,0.71484375
66,0.6171875
67,0.6796875
68,0.46875
69,0.6796875
71,0.58984375
72,0.671875
73,0.640625
74,0.703125
75,0.71484375
76,0.6171875
77,0.7421875
78,0.68359375
79,0.609375
81,0.63671875
82,0.6015625
83,0.49609375
84,0.6875
85,0.71484375
86,0.609375
87,0.62109375
88,0.58984375
89,0.59765625
91,0.640625
92,0.609375
93,0.83203125
94,0.76171875
95,0.68359375
96,0.67578125
97,0.5625
98,0.609375
99,0.578125