Files
llama-3-8b-base-new-dpo-hh-…/train_results.json
ModelHub XC 57d42d92cc 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star0.85-4xh200-batch-64-20260421-233802
Source: Original Platform
2026-06-06 12:06:39 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.8947697063024523,
"train_runtime": 1846.2605,
"train_samples": 43598,
"train_samples_per_second": 23.614,
"train_steps_per_second": 0.369
}