Files
Qwen1.5-MOE-sft-ESFT-law/train_results.json
ModelHub XC 4d41752c94 初始化项目,由ModelHub XC社区提供模型
Model: jayzou3773/Qwen1.5-MOE-sft-ESFT-law
Source: Original Platform
2026-06-05 02:12:02 +08:00

8 lines
216 B
JSON

{
"total_flos": 1.2005510253379584e+17,
"train_loss": 0.40030854754149914,
"train_runtime": 469.3197,
"train_samples": 927,
"train_samples_per_second": 7.901,
"train_steps_per_second": 0.247
}