Files
Qwen1.5-MOE-sft-math7k-dens…/train_results.json
ModelHub XC 8b6e8f053d 初始化项目,由ModelHub XC社区提供模型
Model: xd2010/Qwen1.5-MOE-sft-math7k-densemixer
Source: Original Platform
2026-05-15 21:29:47 +08:00

8 lines
206 B
JSON

{
"total_flos": 20312064000.0,
"train_loss": 0.8405675888061523,
"train_runtime": 27.3869,
"train_samples": 6851,
"train_samples_per_second": 1.168,
"train_steps_per_second": 0.037
}