promotion/ronpo-qwen3-8b-fair-dpo-s42
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: promotion/ronpo-qwen3-8b-fair-dpo-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 16:12:11 +08:00
commit c5827a4516
18 changed files with 4248 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
experiment/training_status.json Normal file
View File

@@ -0,0 +1,20 @@
{
"status": "completed",
"candidate_id": "dpo_b",
"method": "dpo",
"seed": 42,
"gpu": 0,
"pid": 423793,
"config": "/NHNHOME/26msit001_A/BASE/AIPR/sjkim/revision_qwen3_8b/full_iter1/fair_demo_20260715/sweep/candidates/dpo_b/config.yaml",
"dataset": "/NHNHOME/26msit001_A/BASE/AIPR/sjkim/revision_qwen3_8b/full_iter1/flagship_20260712/precomputed/avg",
"optimizer_steps": 900,
"effective_batch_size": 16,
"wandb_run_id": "bce8f73e973a",
"wandb_url": "https://wandb.ai/promotion-kim/mnpo/runs/bce8f73e973a",
"started_at": "2026-07-15T11:34:23+09:00",
"returncode": 0,
"model_complete": true,
"finite_results": true,
"measured_step": null,
"completed_at": "2026-07-15T13:36:52+09:00"
}