llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5/train_results.json at b90154e69ada3e0815dd918f125b60a14ac0ce2b - llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5 - Gitea: Git with a cup of tea

W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5

Files

ModelHub XC b90154e69a 初始化项目，由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5
Source: Original Platform

2026-05-20 02:23:33 +08:00

9 lines

229 B

JSON

Raw Blame History

 {
     "epoch": 0.999244142101285,
     "total_flos": 0.0,
     "train_loss": 1.132411924234497,
     "train_runtime": 1654.1278,
     "train_samples": 42336,
     "train_samples_per_second": 25.594,
     "train_steps_per_second": 0.4
 }