Files
qwen3-8b-base-beta-dpo-hh-h…/train_results.json
ModelHub XC d8351d8ef7 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
Source: Original Platform
2026-05-12 21:11:43 +08:00

9 lines
232 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1644051905929953,
"train_runtime": 2186.2877,
"train_samples": 42336,
"train_samples_per_second": 19.364,
"train_steps_per_second": 0.302
}