qwen3-8b-base-sft-hh-helpful-8xh200/train_results.json at c07cf6deff692e261e485d19907ff894af79ee7c - qwen3-8b-base-sft-hh-helpful-8xh200 - Gitea: Git with a cup of tea

W-61/qwen3-8b-base-sft-hh-helpful-8xh200

Files

ModelHub XC c07cf6deff 初始化项目，由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-sft-hh-helpful-8xh200
Source: Original Platform

2026-04-20 18:45:15 +08:00

9 lines

235 B

JSON

Raw Blame History

 {
     "epoch": 1.0,
     "total_flos": 5.022030486516531e+16,
     "train_loss": 1.7195094338169805,
     "train_runtime": 501.5523,
     "train_samples": 43598,
     "train_samples_per_second": 34.284,
     "train_steps_per_second": 0.269
 }