初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/qwen3-4b-material-grpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-11 00:45:12 +08:00
commit d95aa071a5
17 changed files with 152421 additions and 0 deletions

11
eval_mean16.csv Normal file
View File

@@ -0,0 +1,11 @@
step,mean16
10,0.6775265957446809
20,0.7253989361702128
30,0.7712765957446809
40,0.7832446808510638
50,0.5877659574468085
60,0.6163563829787234
70,0.7001329787234043
80,0.668218085106383
90,0.6788563829787234
100,0.6615691489361702
1 step mean16
2 10 0.6775265957446809
3 20 0.7253989361702128
4 30 0.7712765957446809
5 40 0.7832446808510638
6 50 0.5877659574468085
7 60 0.6163563829787234
8 70 0.7001329787234043
9 80 0.668218085106383
10 90 0.6788563829787234
11 100 0.6615691489361702