Qwen3-1.7B-SFT-science-2e-5/train_results.json at main - Qwen3-1.7B-SFT-science-2e-5 - Gitea: Git with a cup of tea

graf/Qwen3-1.7B-SFT-science-2e-5

Files

ModelHub XC 2bceff8ff1 初始化项目，由ModelHub XC社区提供模型

Model: graf/Qwen3-1.7B-SFT-science-2e-5
Source: Original Platform

2026-05-19 03:36:33 +08:00

8 lines

209 B

JSON

Raw Permalink Blame History

 {
     "epoch": 3.0,
     "total_flos": 4.1917370482093916e+18,
     "train_loss": 0.06833103949818527,
     "train_runtime": 3477.4713,
     "train_samples_per_second": 85.09,
     "train_steps_per_second": 0.665
 }