llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.85/train_results.json at 36da24c147c445cc435346982aec0c6cd1933a02 - llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.85 - 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-0.85

Files

ModelHub XC 36da24c147 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-0.85
Source: Original Platform

2026-06-18 23:09:55 +08:00

9 lines

218 B

JSON

Raw Blame History

 {
     "epoch": 1.0,
     "total_flos": 0.0,
     "train_loss": 0.8810622134572784,
     "train_runtime": 1867.9067,
     "train_samples": 43598,
     "train_samples_per_second": 23.341,
     "train_steps_per_second": 0.365
 }