llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05/train_results.json at aef2411924440c971e4c6d76120b7d778cd0d65d - llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05 - 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-0.05

Files

ModelHub XC aef2411924 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-0.05
Source: Original Platform

2026-05-18 22:13:03 +08:00

9 lines

218 B

JSON

Raw Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 1.0870012780118095,
     "train_runtime": 1735.4876,
     "train_samples": 43598,
     "train_samples_per_second": 25.121,
     "train_steps_per_second": 0.392
 }