W-61/llama-3-8b-base-margin-dpo-hh-helpful-8xh200
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: W-61/llama-3-8b-base-margin-dpo-hh-helpful-8xh200
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-24 11:44:07 +08:00
commit 444c4324b6
361 changed files with 6357 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
all_results.json Normal file
View File

@@ -0,0 +1,22 @@
{
"epoch": 1.0,
"eval_logits/chosen": -0.5745480060577393,
"eval_logits/rejected": -0.535261869430542,
"eval_logps/chosen": -119.71295928955078,
"eval_logps/ref_chosen": -97.0617446899414,
"eval_logps/ref_rejected": -80.18183135986328,
"eval_logps/rejected": -113.98292541503906,
"eval_loss": 0.4582546055316925,
"eval_margin_dpo/margin_mean": 11.149892807006836,
"eval_margin_dpo/margin_std": 15.04123592376709,
"eval_runtime": 20.2691,
"eval_samples": 2339,
"eval_samples_per_second": 115.397,
"eval_steps_per_second": 0.937,
"total_flos": 0.0,
"train_loss": 0.4133688477908864,
"train_runtime": 1436.8705,
"train_samples": 43598,
"train_samples_per_second": 30.342,
"train_steps_per_second": 0.237
}