llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4/train_results.json at main - llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4 - Gitea: Git with a cup of tea

W-61/llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4

Files

ModelHub XC af60501145 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-s_star-0.4-eta-0.1-q_t-0.4
Source: Original Platform

2026-05-18 06:10:14 +08:00

9 lines

214 B

JSON

Raw Permalink Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 1.127045486467,
     "train_runtime": 1737.1181,
     "train_samples": 43598,
     "train_samples_per_second": 25.098,
     "train_steps_per_second": 0.392
 }