Files
llama-3-8b-base-new-dpo-hh-…/train_results.json
ModelHub XC d3c3a1d138 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_star0.6-4xh200-batch-64-20260421-214335-rerun
Source: Original Platform
2026-04-27 09:47:36 +08:00

9 lines
218 B
JSON

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.9952153347312266,
"train_runtime": 1856.6581,
"train_samples": 43598,
"train_samples_per_second": 23.482,
"train_steps_per_second": 0.367
}