Files
Qwen1.5-MOE-sft-ESFT-intent/train_results.json
ModelHub XC 22aa64164f 初始化项目,由ModelHub XC社区提供模型
Model: jayzou3773/Qwen1.5-MOE-sft-ESFT-intent
Source: Original Platform
2026-05-15 09:11:48 +08:00

8 lines
218 B
JSON

{
"total_flos": 1.0952542154391552e+17,
"train_loss": 0.13070940664814165,
"train_runtime": 1765.7438,
"train_samples": 7280,
"train_samples_per_second": 8.246,
"train_steps_per_second": 0.258
}