qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42/train_results.json at 0738f2ca0a204007eda117fcfcaf045321f5f7c6 - qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42 - Gitea: Git with a cup of tea

promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42

Files

ModelHub XC 0738f2ca0a 初始化项目，由ModelHub XC社区提供模型

Model: promotion/qwen3-8b-aaai27-flagship-ht-mnpo-helpfulness-s42
Source: Original Platform

2026-07-23 13:58:09 +08:00

9 lines

232 B

JSON

Raw Blame History

 {
     "epoch": 0.8600609209819029,
     "total_flos": 0.0,
     "train_loss": 0.3323093075222439,
     "train_runtime": 7030.1668,
     "train_samples": 16743,
     "train_samples_per_second": 2.048,
     "train_steps_per_second": 0.128
 }