Files
ronpo-qwen3-8b-fair-inpo-av…/train_results.json
ModelHub XC a0bc76759a 初始化项目,由ModelHub XC社区提供模型
Model: promotion/ronpo-qwen3-8b-fair-inpo-avg-s42
Source: Original Platform
2026-07-18 11:48:10 +08:00

9 lines
232 B
JSON

{
"epoch": 0.8599068434252956,
"total_flos": 0.0,
"train_loss": 24.184869588216145,
"train_runtime": 7109.0777,
"train_samples": 16746,
"train_samples_per_second": 2.026,
"train_steps_per_second": 0.127
}