Files
qwen3-4b-think-s1-ep23-full…/train_results.json
ModelHub XC 07a669f2ad 初始化项目,由ModelHub XC社区提供模型
Model: modrill/qwen3-4b-think-s1-ep23-full-sft
Source: Original Platform
2026-09-26 09:49:16 +08:00

8 lines
204 B
JSON

{
"epoch": 2.0,
"total_flos": 1116023864426496.0,
"train_loss": 0.5415504160306311,
"train_runtime": 61158.2606,
"train_samples_per_second": 0.631,
"train_steps_per_second": 0.01
}