qwen3-8B-sft-mix-v20250921/train_results.json at main - qwen3-8B-sft-mix-v20250921 - Gitea: Git with a cup of tea

rl-rag/qwen3-8B-sft-mix-v20250921

Files

ModelHub XC 08c29fba95 初始化项目，由ModelHub XC社区提供模型

Model: rl-rag/qwen3-8B-sft-mix-v20250921
Source: Original Platform

2026-08-04 11:17:18 +08:00

8 lines

204 B

JSON

Raw Permalink Blame History

 {
     "epoch": 5.0,
     "total_flos": 1235947560108032.0,
     "train_loss": 0.7053156269921197,
     "train_runtime": 61423.1886,
     "train_samples_per_second": 1.307,
     "train_steps_per_second": 0.01
 }