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

1.4 KiB

1stepcritic_score_mean
210.57421875
320.3515625
430.4453125
540.375
650.4609375
760.4453125
870.38671875
980.52734375
1090.3671875
11100.40234375
12110.4609375
13120.48046875
14130.4921875
15140.3828125
16150.4921875
17160.42578125
18170.41015625
19180.4140625
20190.515625
21200.53125
22210.4140625
23220.34765625
24230.58203125
25240.5703125
26250.48046875
27260.5546875
28270.421875
29280.5859375
30290.421875
31300.44921875
32310.5859375
33320.53515625
34330.5859375
35340.49609375
36350.49609375
37360.6171875
38370.51953125
39380.58203125
40390.53515625
41400.4921875
42410.51171875
43420.55078125
44430.59375
45440.58984375
46450.51171875
47460.4921875
48470.59375
49480.58984375
50490.6875
51500.62109375
52510.4921875
53520.55078125
54530.61328125
55540.5234375
56550.65625
57560.58203125
58570.578125
59580.6015625
60590.5390625
61600.671875
62610.6171875
63620.59765625
64630.51953125
65640.73828125
66650.6796875
67660.56640625
68670.6875
69680.40625
70690.6015625
71700.59375
72710.55078125
73720.67578125
74730.55078125
75740.5859375
76750.75390625
77760.5
78770.7265625
79780.640625
80790.55078125
81800.68359375
82810.57421875
83820.5078125
84830.46875
85840.6328125
86850.671875
87860.49609375
88870.45703125
89880.546875
90890.52734375
91900.51953125
92910.57421875
93920.578125
94930.8671875
95940.71484375
96950.640625
97960.6171875
98970.5390625
99980.51953125
100990.6328125
1011000.62890625