Files
Qwen3-4B-Chemical-GRPO-TR/results/training_scores.csv
ModelHub XC 1700d223a4 初始化项目,由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Chemical-GRPO-TR
Source: Original Platform
2026-08-09 20:57:18 +08:00

102 lines
1.4 KiB
CSV

step,critic_score_mean
1,0.57421875
2,0.3515625
3,0.4453125
4,0.375
5,0.4609375
6,0.4453125
7,0.38671875
8,0.52734375
9,0.3671875
10,0.40234375
11,0.4609375
12,0.48046875
13,0.4921875
14,0.3828125
15,0.4921875
16,0.42578125
17,0.41015625
18,0.4140625
19,0.515625
20,0.53125
21,0.4140625
22,0.34765625
23,0.58203125
24,0.5703125
25,0.48046875
26,0.5546875
27,0.421875
28,0.5859375
29,0.421875
30,0.44921875
31,0.5859375
32,0.53515625
33,0.5859375
34,0.49609375
35,0.49609375
36,0.6171875
37,0.51953125
38,0.58203125
39,0.53515625
40,0.4921875
41,0.51171875
42,0.55078125
43,0.59375
44,0.58984375
45,0.51171875
46,0.4921875
47,0.59375
48,0.58984375
49,0.6875
50,0.62109375
51,0.4921875
52,0.55078125
53,0.61328125
54,0.5234375
55,0.65625
56,0.58203125
57,0.578125
58,0.6015625
59,0.5390625
60,0.671875
61,0.6171875
62,0.59765625
63,0.51953125
64,0.73828125
65,0.6796875
66,0.56640625
67,0.6875
68,0.40625
69,0.6015625
70,0.59375
71,0.55078125
72,0.67578125
73,0.55078125
74,0.5859375
75,0.75390625
76,0.5
77,0.7265625
78,0.640625
79,0.55078125
80,0.68359375
81,0.57421875
82,0.5078125
83,0.46875
84,0.6328125
85,0.671875
86,0.49609375
87,0.45703125
88,0.546875
89,0.52734375
90,0.51953125
91,0.57421875
92,0.578125
93,0.8671875
94,0.71484375
95,0.640625
96,0.6171875
97,0.5390625
98,0.51953125
99,0.6328125
100,0.62890625