Files
Qwen1.5-MOE-sft-ESFT-transl…/train_results.json
ModelHub XC d3da1a674f 初始化项目,由ModelHub XC社区提供模型
Model: jayzou3773/Qwen1.5-MOE-sft-ESFT-translation
Source: Original Platform
2026-05-27 05:08:19 +08:00

8 lines
216 B
JSON

{
"total_flos": 4.595247209544417e+17,
"train_loss": 1.052156428714375,
"train_runtime": 2874.0296,
"train_samples": 11639,
"train_samples_per_second": 8.099,
"train_steps_per_second": 0.253
}