Files
llama-3-8b-base-beta-dpo-hh…/train_results.json
ModelHub XC 8162a32e06 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539
Source: Original Platform
2026-05-30 22:45:37 +08:00

9 lines
230 B
JSON

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1692889305268401,
"train_runtime": 3152.686,
"train_samples": 42336,
"train_samples_per_second": 13.429,
"train_steps_per_second": 0.21
}