Qwen3-1.7B-SFT-100k/train_results.json at aaf1107285d85732a8bb6609dad5843dbd5a1642 - Qwen3-1.7B-SFT-100k - Gitea: Git with a cup of tea

oodgnas/Qwen3-1.7B-SFT-100k

Files

ModelHub XC aaf1107285 初始化项目，由ModelHub XC社区提供模型

Model: oodgnas/Qwen3-1.7B-SFT-100k
Source: Original Platform

2026-08-20 14:15:17 +08:00

8 lines

203 B

JSON

Raw Blame History

 {
     "epoch": 3.0,
     "total_flos": 145115603533824.0,
     "train_loss": 0.698847218818268,
     "train_runtime": 3222.3497,
     "train_samples_per_second": 29.579,
     "train_steps_per_second": 0.463
 }