SeongryongJung/Qwen3-4B-Biology-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-Biology-GRPO-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-03 20:15:22 +08:00
commit 7d17112db8
38 changed files with 317443 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
results/export_note.csv Normal file
View File

@@ -0,0 +1,7 @@
key,value
root_checkpoint_step,100
root_checkpoint_kind,final
best_validation_step,90
best_validation_mean16,0.467500000000
best_actor_available,false
reason,global_step_90 has validation metadata only; no actor model shards are present
1 key value
2 root_checkpoint_step 100
3 root_checkpoint_kind final
4 best_validation_step 90
5 best_validation_mean16 0.467500000000
6 best_actor_available false
7 reason global_step_90 has validation metadata only; no actor model shards are present