Files
qwen3-8b-base-beta-dpo-hh-h…/train_results.json
ModelHub XC 527c912d5f 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260424-025105
Source: Original Platform
2026-05-16 07:03:57 +08:00

9 lines
232 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1663504292943294,
"train_runtime": 3087.1314,
"train_samples": 42336,
"train_samples_per_second": 13.714,
"train_steps_per_second": 0.214
}