Files
qwen3-8b-base-margin-dpo-hh…/train_results.json
ModelHub XC 4efda549c2 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/qwen3-8b-base-margin-dpo-hh-harmless-4xh200-batch-64-20260423-234249
Source: Original Platform
2026-05-19 02:33:40 +08:00

9 lines
231 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.122965409968516,
"train_runtime": 3224.9347,
"train_samples": 42336,
"train_samples_per_second": 13.128,
"train_steps_per_second": 0.205
}