llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260427-221551/train_results.json at main - llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260427-221551 - Gitea: Git with a cup of tea

W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260427-221551

Files

ModelHub XC ba2948d9f0 初始化项目，由ModelHub XC社区提供模型

Model: W-61/llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.45-20260427-221551
Source: Original Platform

2026-05-04 21:47:48 +08:00

9 lines

230 B

JSON

Raw Permalink Blame History

 {
     "epoch": 0.9989528795811519,
     "total_flos": 0.0,
     "train_loss": 4.705121593155451,
     "train_runtime": 6559.8554,
     "train_samples": 61135,
     "train_samples_per_second": 9.32,
     "train_steps_per_second": 0.073
 }