SeongryongJung/Qwen3-4B-Material-GRPO-TR
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: SeongryongJung/Qwen3-4B-Material-GRPO-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-04 08:21:18 +08:00
commit 5a9933097b
37 changed files with 326337 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
results/validation_mean16.csv Normal file
View File

@@ -0,0 +1,11 @@
step,val_mean16
10,0.6688829787234043
20,0.6954787234042553
30,0.7167553191489362
40,0.7393617021276596
50,0.754654255319149
60,0.7659574468085106
70,0.75
80,0.7506648936170213
90,0.7566489361702128
100,0.7626329787234043
1 step val_mean16
2 10 0.6688829787234043
3 20 0.6954787234042553
4 30 0.7167553191489362
5 40 0.7393617021276596
6 50 0.754654255319149
7 60 0.7659574468085106
8 70 0.75
9 80 0.7506648936170213
10 90 0.7566489361702128
11 100 0.7626329787234043