llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.4/train_results.json at main - llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.4 - Gitea: Git with a cup of tea

jackf857/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.4

Files

ModelHub XC b5cca84e50 初始化项目，由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.4
Source: Original Platform

2026-05-09 11:52:35 +08:00

9 lines

218 B

JSON

Raw Permalink Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 1.0910053594522013,
     "train_runtime": 1869.3984,
     "train_samples": 43598,
     "train_samples_per_second": 23.322,
     "train_steps_per_second": 0.364
 }