Files
qwen3-8b-base-beta-dpo-hh-h…/train_results.json
ModelHub XC 7c5f50b79e 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64
Source: Original Platform
2026-08-05 11:13:18 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 1.1809129529850073,
"train_runtime": 2340.6187,
"train_samples": 43598,
"train_samples_per_second": 18.627,
"train_steps_per_second": 0.291
}