llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8/train_results.json at 02bf1f76cb73516ac4cce846aeaa15a266e2be8f - llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8 - Gitea: Git with a cup of tea

W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8

Files

ModelHub XC 02bf1f76cb 初始化项目，由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8
Source: Original Platform

2026-05-12 14:46:33 +08:00

9 lines

217 B

JSON

Raw Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 1.356521034380763,
     "train_runtime": 1742.8549,
     "train_samples": 43598,
     "train_samples_per_second": 25.015,
     "train_steps_per_second": 0.391
 }